Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
🧠
Processor

Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz

Intel
214Benchmarks
61Models
214Performance
0Harness
25 WIdle power
115 WMax power
Best generation
609,5 tok/s
Llama-3.2-1B-Instruct
∅ Generation
109,0 tok/s
Schnitt aus 214 Läufen
Best prefill
31.648 tok/s
Prompt processing
Best TTFT
400 ms
Time to First Token
Best harness rate
–%
noch kein Harness
🏆
Llama-3.2-1B-Instruct läuft am schnellsten auf dieser CPU · 609,5 tok/s
Bester Prefill: 31.648 tok/s · 61 Modelle getestet

Top models

Bester gemessener Durchsatz je Modell auf Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz – umschaltbar nach Generation, Prefill oder Kombiwert.

Llama-3.2-1B-Instruct1B
609,5 tok/s
Qwen3-0.6B0.6B
480,5 tok/s
Qwen3-1.7B1.7B
437,4 tok/s
Llama-3.2-3B-Instruct3B
354,2 tok/s
Qwen2.5-3B-Instruct3B
333,2 tok/s
gemma-2-2b-it2B
323,8 tok/s
Qwen3-4B4B
294,3 tok/s
Phi-3.5-mini-instruct3.8B
272,9 tok/s
Meta-Llama-3.1-8B-Instruct8B
266,7 tok/s
Qwen2.5-Coder-7B-Instruct
256,7 tok/s
Performance profile

Durchsatz auf Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz

Jede Blase steht für ein Modell, eine Engine bzw. eine GPU – Position: Prompt-Verarbeitung (X) × Ausgabe (Y), Blasengröße: Anzahl Messläufe.

MODnach Modell

7675763841920,008.46216.92425.386Prefill (tok/s)Generation (tok/s)Llama-3.2-1B-Instruct - 609,5 tok/s Generation, 20.528 tok/s Prefill, TTFT 659 ms (3 Laufe)Llama-3.2-1B-InstructQwen3-0.6B - 480,5 tok/s Generation, 14.980 tok/s Prefill, TTFT 819 ms (3 Laufe)Qwen3-0.6BQwen3-1.7B - 437,4 tok/s Generation, 11.792 tok/s Prefill, TTFT 1.033 ms (3 Laufe)Qwen3-1.7BLlama-3.2-3B-Instruct - 354,2 tok/s Generation, 10.737 tok/s Prefill, TTFT 2.277 ms (6 Laufe)Llama-3.2-3B-InstructQwen2.5-3B-Instruct - 333,2 tok/s Generation, 10.446 tok/s Prefill, TTFT 2.268 ms (6 Laufe)Qwen2.5-3B-Instructgemma-2-2b-it - 323,8 tok/s Generation, 5.760 tok/s Prefill, TTFT 2.645 ms (2 Laufe)gemma-2-2b-itQwen3-4B - 294,3 tok/s Generation, 8.420 tok/s Prefill, TTFT 2.305 ms (2 Laufe)Qwen3-4BPhi-3.5-mini-instruct - 272,9 tok/s Generation, 2.958 tok/s Prefill, TTFT 25.143 ms (2 Laufe)Phi-3.5-mini-instructMeta-Llama-3.1-8B-Instruct - 266,7 tok/s Generation, 5.721 tok/s Prefill, TTFT 7.617 ms (4 Laufe)Meta-Llama-3.1-8B-Ins...Qwen2.5-Coder-7B-Instruct - 256,7 tok/s Generation, 8.716 tok/s Prefill, TTFT 2.601 ms (2 Laufe)Qwen2.5-Coder-7B-Inst...Qwen3-8B - 252,8 tok/s Generation, 5.668 tok/s Prefill, TTFT 3.412 ms (2 Laufe)Qwen3-8Bgpt-oss-20b - 247,3 tok/s Generation, 4.978 tok/s Prefill, TTFT 2.960 ms (2 Laufe)gpt-oss-20bNemotron-3-Nano-30B-A3B - 244,9 tok/s Generation, 3.102 tok/s Prefill, TTFT 5.704 ms (2 Laufe)Nemotron-3-Nano-30B-A...Qwen3-Coder-30B-A3B-Instruct - 234,1 tok/s Generation, 6.252 tok/s Prefill, TTFT 3.714 ms (2 Laufe)Qwen3-Coder-30B-A3B-I...Qwen3-30B-A3B - 227,0 tok/s Generation, 4.302 tok/s Prefill, TTFT 4.547 ms (2 Laufe)Qwen3-30B-A3BQwen3-30B-A3B-Thinking-2507 - 223,3 tok/s Generation, 5.450 tok/s Prefill, TTFT 3.625 ms (2 Laufe)Qwen3-30B-A3B-Thinkin...Qwen3-VL-30B-A3B-Instruct - 221,6 tok/s Generation, 5.447 tok/s Prefill, TTFT 4.018 ms (2 Laufe)Qwen3-VL-30B-A3B-Inst...gemma-3n-E4B-it - 220,8 tok/s Generation, 3.758 tok/s Prefill, TTFT 6.047 ms (1 Lauf)gemma-3n-E4B-itQwen3-30B-A3B-Instruct-2507 - 218,5 tok/s Generation, 4.448 tok/s Prefill, TTFT 5.103 ms (2 Laufe)Qwen3-30B-A3B-Instruc...Qwen3-Omni-30B-A3B-Thinking - 218,1 tok/s Generation, 4.138 tok/s Prefill, TTFT 4.692 ms (2 Laufe)Qwen3-Omni-30B-A3B-Th...Laguna-XS-2.1 - 212,4 tok/s Generation, 3.887 tok/s Prefill, TTFT 6.031 ms (2 Laufe)Laguna-XS-2.1North-Mini-Code-1.0 - 208,8 tok/s Generation, 3.100 tok/s Prefill, TTFT 5.195 ms (2 Laufe)North-Mini-Code-1.0Ornith-1.0-9B - 207,5 tok/s Generation, 3.643 tok/s Prefill, TTFT 4.397 ms (2 Laufe)Ornith-1.0-9BMinistral-3-14B-Reasoning-2512 - 204,9 tok/s Generation, 4.780 tok/s Prefill, TTFT 4.095 ms (2 Laufe)Ministral-3-14B-Reaso...Qwen3-Coder-Next - 197,7 tok/s Generation, 3.028 tok/s Prefill, TTFT 9.922 ms (1 Lauf)Qwen3-Coder-NextQwen3-14B - 186,9 tok/s Generation, 4.086 tok/s Prefill, TTFT 6.892 ms (1 Lauf)Qwen3-14BGemma-4-26B-A4B-it - 185,7 tok/s Generation, 1.945 tok/s Prefill, TTFT 7.711 ms (2 Laufe)Gemma-4-26B-A4B-itQwen3.5-35B-A3B - 184,4 tok/s Generation, 3.495 tok/s Prefill, TTFT 4.637 ms (2 Laufe)Qwen3.5-35B-A3BQwen3.6-35B-A3B - 181,7 tok/s Generation, 3.591 tok/s Prefill, TTFT 4.478 ms (2 Laufe)Qwen3.6-35B-A3Bgemma-4-12B-it - 179,4 tok/s Generation, 755 tok/s Prefill, TTFT 26.574 ms (1 Lauf)gemma-4-12B-itQwen-AgentWorld-35B-A3B - 177,0 tok/s Generation, 3.900 tok/s Prefill, TTFT 5.890 ms (1 Lauf)Qwen-AgentWorld-35B-A...gemma-2-9b-it - 171,6 tok/s Generation, 378 tok/s Prefill, TTFT 49.531 ms (1 Lauf)gemma-2-9b-itMistral-Small-3.1-24B-Instruct-2503 - 170,1 tok/s Generation, 4.885 tok/s Prefill, TTFT 6.913 ms (1 Lauf)Mistral-Small-3.1-24B...Magistral-Small-2509 - 170,0 tok/s Generation, 3.644 tok/s Prefill, TTFT 7.723 ms (1 Lauf)Magistral-Small-2509Devstral-Small-2-24B-Instruct-2512 - 162,7 tok/s Generation, 4.605 tok/s Prefill, TTFT 6.779 ms (1 Lauf)Devstral-Small-2-24B-...Devstral-Small-2507 - 161,8 tok/s Generation, 4.897 tok/s Prefill, TTFT 6.307 ms (2 Laufe)Devstral-Small-2507Qwen2.5-7B-Instruct - 160,3 tok/s Generation, 4.979 tok/s Prefill, TTFT 6.510 ms (1 Lauf)Qwen2.5-7B-InstructCodestral-22B-v0.1 - 154,1 tok/s Generation, 4.443 tok/s Prefill, TTFT 9.034 ms (1 Lauf)Codestral-22B-v0.1Mistral-Small-24B-Instruct-2501 - 153,1 tok/s Generation, 4.348 tok/s Prefill, TTFT 7.017 ms (1 Lauf)Mistral-Small-24B-Ins...OpenReasoning-Nemotron-32B - 124,6 tok/s Generation, 2.910 tok/s Prefill, TTFT 13.342 ms (1 Lauf)OpenReasoning-Nemotro...
Llama-3.2-1B-Instruct 609,5 tok/sQwen3-0.6B 480,5 tok/sQwen3-1.7B 437,4 tok/sLlama-3.2-3B-Instruct 354,2 tok/sQwen2.5-3B-Instruct 333,2 tok/sgemma-2-2b-it 323,8 tok/sQwen3-4B 294,3 tok/sPhi-3.5-mini-instruct 272,9 tok/sMeta-Llama-3.1-8B-Instruct 266,7 tok/sQwen2.5-Coder-7B-Instruct 256,7 tok/sQwen3-8B 252,8 tok/sgpt-oss-20b 247,3 tok/sNemotron-3-Nano-30B-A3B 244,9 tok/sQwen3-Coder-30B-A3B-Instruct 234,1 tok/sQwen3-30B-A3B 227,0 tok/sQwen3-30B-A3B-Thinking-2507 223,3 tok/sQwen3-VL-30B-A3B-Instruct 221,6 tok/sgemma-3n-E4B-it 220,8 tok/sQwen3-30B-A3B-Instruct-2507 218,5 tok/sQwen3-Omni-30B-A3B-Thinking 218,1 tok/sLaguna-XS-2.1 212,4 tok/sNorth-Mini-Code-1.0 208,8 tok/sOrnith-1.0-9B 207,5 tok/sMinistral-3-14B-Reasoning-2512 204,9 tok/sQwen3-Coder-Next 197,7 tok/sQwen3-14B 186,9 tok/sGemma-4-26B-A4B-it 185,7 tok/sQwen3.5-35B-A3B 184,4 tok/sQwen3.6-35B-A3B 181,7 tok/sgemma-4-12B-it 179,4 tok/sQwen-AgentWorld-35B-A3B 177,0 tok/sgemma-2-9b-it 171,6 tok/sMistral-Small-3.1-24B-Instruct-2503 170,1 tok/sMagistral-Small-2509 170,0 tok/sDevstral-Small-2-24B-Instruct-2512 162,7 tok/sDevstral-Small-2507 161,8 tok/sQwen2.5-7B-Instruct 160,3 tok/sCodestral-22B-v0.1 154,1 tok/sMistral-Small-24B-Instruct-2501 153,1 tok/sOpenReasoning-Nemotron-32B 124,6 tok/s

ENGnach Engine

75957438920519,91.5533.6835.8137.942Prefill (tok/s)Generation (tok/s)llama.cpp - 609,5 tok/s Generation, 6.797 tok/s Prefill, TTFT 5.499 ms (78 Laufe)llama.cppvLLM - 169,0 tok/s Generation, 2.698 tok/s Prefill, TTFT 12.570 ms (2 Laufe)vLLM
llama.cpp 609,5 tok/svLLM 169,0 tok/s

GPUnach Grafikkarte

7405884352821296.1226.6157.1087.601Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 609,5 tok/s Generation, 6.631 tok/s Prefill, TTFT 5.814 ms (69 Laufe)AMD Radeon RX 7900 XTXNVIDIA GeForce RTX 2060 - 259,9 tok/s Generation, 7.093 tok/s Prefill, TTFT 4.812 ms (11 Laufe)NVIDIA GeForce RTX 20...
AMD Radeon RX 7900 XTX 609,5 tok/sNVIDIA GeForce RTX 2060 259,9 tok/s
Platform

Mainboards with this CPU

Auf diesen Boards wurde Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz gemessen – anklicken für Board-Details mit CPUs und Modellen.

🧮Dell Inc. PowerEdge R820Dell · 61 Modelle · 214 Läufe · bis 609,5 tok/s→
Throughput & latency

Performancebenchmark

80 veroeffentlichte Performance-Läufe auf Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz.

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
609,48 tok/s TG
Prefill 31.648 · TTFT 962 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
2Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
480,52 tok/s TG
Prefill 22.887 · TTFT 1.208 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
3Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
437,40 tok/s TG
Prefill 16.731 · TTFT 1.636 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
4Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
376,49 tok/s TG
Prefill 22.247 · TTFT 615 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
5Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
354,21 tok/s TG
Prefill 17.373 · TTFT 1.825 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
6Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
333,18 tok/s TG
Prefill 17.060 · TTFT 1.879 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
7gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
323,81 tok/s TG
Prefill 6.071 · TTFT 3.506 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
8Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
294,28 tok/s TG
Prefill 9.688 · TTFT 2.856 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
9Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
281,62 tok/s TG
Prefill 14.942 · TTFT 839 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
10Phi-3.5-mini-instruct3.8Bmicrosoft Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
272,93 tok/s TG
Prefill 691 · TTFT 38.379 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
11Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
268,79 tok/s TG
Prefill 12.537 · TTFT 993 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
12Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
266,70 tok/s TG
Prefill 10.161 · TTFT 3.360 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
13Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
259,86 tok/s TG
Prefill 9.253 · TTFT 3.361 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
14Qwen2.5-Coder-7B-InstructQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
256,72 tok/s TG
Prefill 10.123 · TTFT 3.280 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
15Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
252,78 tok/s TG
Prefill 6.452 · TTFT 4.269 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
16gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
247,27 tok/s TG
Prefill 5.437 · TTFT 3.732 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
17Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
244,91 tok/s TG
Prefill 3.719 · TTFT 6.905 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
18Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
234,08 tok/s TG
Prefill 7.116 · TTFT 4.629 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
19Qwen3-30B-A3B30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
226,96 tok/s TG
Prefill 5.032 · TTFT 5.593 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
20Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
226,59 tok/s TG
Prefill 9.526 · TTFT 3.488 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
21Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
225,82 tok/s TG
Prefill 9.739 · TTFT 3.277 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
22Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
223,26 tok/s TG
Prefill 5.840 · TTFT 4.476 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
23Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
221,62 tok/s TG
Prefill 6.455 · TTFT 4.958 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
24gemma-3n-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
220,77 tok/s TG
Prefill 3.758 · TTFT 6.047 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
25Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
218,45 tok/s TG
Prefill 4.085 · TTFT 7.280 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
26Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
218,13 tok/s TG
Prefill 4.747 · TTFT 5.848 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
27Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
215,97 tok/s TG
Prefill 9.775 · TTFT 3.283 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
28gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
212,46 tok/s TG
Prefill 5.449 · TTFT 1.783 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
29Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
212,42 tok/s TG
Prefill 4.204 · TTFT 7.880 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
30North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
208,75 tok/s TG
Prefill 3.396 · TTFT 6.675 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
31Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
207,49 tok/s TG
Prefill 4.026 · TTFT 5.675 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
32Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
207,49 tok/s TG
Prefill 12.047 · TTFT 1.151 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
33Llama-3.2-1B-Instruct1BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
207,12 tok/s TG
Prefill 7.688 · TTFT 400 ms
1×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
34Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
204,85 tok/s TG
Prefill 5.517 · TTFT 5.147 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
35Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
197,72 tok/s TG
Prefill 3.028 · TTFT 9.922 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
36Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
196,57 tok/s TG
Prefill 12.975 · TTFT 1.133 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
37gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
192,70 tok/s TG
Prefill 4.519 · TTFT 2.188 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
38Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
187,50 tok/s TG
Prefill 6.698 · TTFT 2.090 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
39Qwen3-14B14BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
186,94 tok/s TG
Prefill 4.086 · TTFT 6.892 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
40Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
185,72 tok/s TG
Prefill 2.040 · TTFT 10.071 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
41Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
185,17 tok/s TG
Prefill 2.486 · TTFT 4.503 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
42Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
184,99 tok/s TG
Prefill 7.151 · TTFT 1.754 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
43Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
184,38 tok/s TG
Prefill 3.855 · TTFT 5.993 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
44Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
181,73 tok/s TG
Prefill 3.947 · TTFT 5.816 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
45gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
179,37 tok/s TG
Prefill 755 · TTFT 26.574 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
46Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
177,00 tok/s TG
Prefill 3.900 · TTFT 5.890 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
47Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
173,08 tok/s TG
Prefill 7.158 · TTFT 2.024 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
48Phi-3.5-mini-instruct3.8Bmicrosoft Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
172,34 tok/s TG
Prefill 5.226 · TTFT 11.908 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
49gemma-2-9b-it9BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
171,56 tok/s TG
Prefill 378 · TTFT 49.531 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
50Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
170,07 tok/s TG
Prefill 4.885 · TTFT 6.913 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
51Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
170,04 tok/s TG
Prefill 3.644 · TTFT 7.723 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
52Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
168,96 tok/s TG
Prefill 3.010 · TTFT 18.082 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMvLLMgodclawAWQDetails →
53Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
168,19 tok/s TG
Prefill 7.879 · TTFT 1.850 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
54Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
162,67 tok/s TG
Prefill 4.605 · TTFT 6.779 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
55Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
161,82 tok/s TG
Prefill 5.708 · TTFT 7.791 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
56Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
160,26 tok/s TG
Prefill 4.979 · TTFT 6.510 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
57Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
158,98 tok/s TG
Prefill 4.810 · TTFT 2.927 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
58Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
158,90 tok/s TG
Prefill 7.616 · TTFT 1.908 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
59Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
157,44 tok/s TG
Prefill 5.388 · TTFT 2.798 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
60Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
154,06 tok/s TG
Prefill 4.443 · TTFT 9.034 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
61Mistral-Small-24B-Instruct-2501Mistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
153,12 tok/s TG
Prefill 4.348 · TTFT 7.017 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
62Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
152,06 tok/s TG
Prefill 7.328 · TTFT 1.967 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
63Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
151,93 tok/s TG
Prefill 3.571 · TTFT 4.182 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
64Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
151,56 tok/s TG
Prefill 5.059 · TTFT 2.775 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
65Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
150,92 tok/s TG
Prefill 4.439 · TTFT 3.079 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
66Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
150,76 tok/s TG
Prefill 3.259 · TTFT 3.120 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
67Qwen2.5-Coder-7B-InstructQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
148,60 tok/s TG
Prefill 7.309 · TTFT 1.923 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
68Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
145,20 tok/s TG
Prefill 4.884 · TTFT 2.555 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
69Qwen3-0.6B0.6BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
143,39 tok/s TG
Prefill 7.110 · TTFT 411 ms
1×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
70Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
136,39 tok/s TG
Prefill 3.136 · TTFT 3.281 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
71Qwen3-1.7B1.7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
136,10 tok/s TG
Prefill 6.107 · TTFT 471 ms
1×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
72Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
134,94 tok/s TG
Prefill 4.042 · TTFT 3.043 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
73Qwen3-30B-A3B30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
132,32 tok/s TG
Prefill 3.572 · TTFT 3.501 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
74North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
127,13 tok/s TG
Prefill 2.805 · TTFT 3.716 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
75Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
126,81 tok/s TG
Prefill 3.529 · TTFT 3.536 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
76Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
126,19 tok/s TG
Prefill 4.087 · TTFT 4.824 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
77OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
124,63 tok/s TG
Prefill 2.910 · TTFT 13.342 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
78Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
124,06 tok/s TG
Prefill 1.850 · TTFT 5.352 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
79Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
122,88 tok/s TG
Prefill 2.387 · TTFT 7.059 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMvLLMgodclawAWQDetails →
80Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
117,49 tok/s TG
Prefill 3.235 · TTFT 3.141 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz.

In the leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← All hardware

Technische Daten

Technische Daten – Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz

HerstellerIntel
TDP115 W
Best generation609,5 tok/s
Best prefill31.648 tok/s
Models61
Messläufe (Performance)214