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

NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU)

Intel
20Benchmarks
5Models
20Performance
0Harness
Best generation
200,5 tok/s
gpt-oss-20b
∅ Generation
93,5 tok/s
Schnitt aus 20 Läufen
Best prefill
5.833 tok/s
Prompt processing
Best TTFT
846 ms
Time to First Token
Best harness rate
–%
noch kein Harness
🏆
gpt-oss-20b läuft am schnellsten auf dieser CPU · 200,5 tok/s
Bester Prefill: 5.833 tok/s · 5 Modelle getestet

Top models

Bester gemessener Durchsatz je Modell auf NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) – umschaltbar nach Generation, Prefill oder Kombiwert.

gpt-oss-20b20B
200,5 tok/s
Nemotron-3.5-Lightning-30B-A3B30B
146,9 tok/s
Qwen3.6-35B-A3B35B
142,0 tok/s
gpt-oss-120b120B
111,9 tok/s
Qwen3-30B-A3B-Thinking-250730B
107,0 tok/s
Performance profile

Durchsatz auf NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU)

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

MODnach Modell

23919615411168,27441.8462.9484.049Prefill (tok/s)Generation (tok/s)gpt-oss-20b - 200,5 tok/s Generation, 3.459 tok/s Prefill, TTFT 3.538 ms (4 Laufe)gpt-oss-20bNemotron-3.5-Lightning-30B-A3B - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe)Nemotron-3.5-Lightnin...Qwen3.6-35B-A3B - 142,0 tok/s Generation, 2.336 tok/s Prefill, TTFT 5.494 ms (4 Laufe)Qwen3.6-35B-A3Bgpt-oss-120b - 111,9 tok/s Generation, 1.334 tok/s Prefill, TTFT 8.374 ms (4 Laufe)gpt-oss-120bQwen3-30B-A3B-Thinking-2507 - 107,0 tok/s Generation, 2.977 tok/s Prefill, TTFT 7.500 ms (4 Laufe)Qwen3-30B-A3B-Thinkin...
gpt-oss-20b 200,5 tok/sNemotron-3.5-Lightning-30B-A3B 146,9 tok/sQwen3.6-35B-A3B 142,0 tok/sgpt-oss-120b 111,9 tok/sQwen3-30B-A3B-Thinking-2507 107,0 tok/s

ENGnach Engine

2212102001901802.2452.3412.4362.532Prefill (tok/s)Generation (tok/s)llama.cpp - 200,5 tok/s Generation, 2.388 tok/s Prefill, TTFT 6.128 ms (20 Laufe)llama.cpp
llama.cpp 200,5 tok/s

GPUnach Grafikkarte

2212102001901802.2452.3412.4362.532Prefill (tok/s)Generation (tok/s)NVIDIA RTX SPARK (N1X) - 200,5 tok/s Generation, 2.388 tok/s Prefill, TTFT 6.128 ms (20 Laufe)NVIDIA RTX SPARK (N1X)
NVIDIA RTX SPARK (N1X) 200,5 tok/s
Platform

Mainboards with this CPU

Auf diesen Boards wurde NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) gemessen – anklicken für Board-Details mit CPUs und Modellen.

🧮ASUS H7607BAASUS · 5 Modelle · 20 Läufe · bis 200,5 tok/s→
Throughput & latency

Performancebenchmark

20 veroeffentlichte Performance-Läufe auf NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU).

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
200,47 tok/s TG
Prefill 5.303 · TTFT 7.750 ms
10×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
2Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
146,86 tok/s TG
Prefill 2.806 · TTFT 12.191 ms
10×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_0Details →
3Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
141,98 tok/s TG
Prefill 4.212 · TTFT 12.237 ms
10×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
4Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
124,89 tok/s TG
Prefill 2.476 · TTFT 6.821 ms
5×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
5Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
121,80 tok/s TG
Prefill 1.943 · TTFT 7.408 ms
5×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_0Details →
6gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
119,73 tok/s TG
Prefill 3.482 · TTFT 4.698 ms
5×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
7gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
111,85 tok/s TG
Prefill 2.041 · TTFT 17.689 ms
10×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
8Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
106,99 tok/s TG
Prefill 5.833 · TTFT 17.334 ms
10×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
9gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
79,06 tok/s TG
Prefill 1.478 · TTFT 11.284 ms
5×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
10Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,08 tok/s TG
Prefill 1.575 · TTFT 1.551 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
11Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
72,08 tok/s TG
Prefill 1.293 · TTFT 1.669 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_0Details →
12Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
71,97 tok/s TG
Prefill 3.029 · TTFT 9.456 ms
5×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
13gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
70,74 tok/s TG
Prefill 2.529 · TTFT 846 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
14Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
67,87 tok/s TG
Prefill 1.288 · TTFT 1.499 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
15Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
66,20 tok/s TG
Prefill 1.300 · TTFT 1.660 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_0Details →
16Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
64,50 tok/s TG
Prefill 1.366 · TTFT 1.420 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
17gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
64,41 tok/s TG
Prefill 2.523 · TTFT 858 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
18Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
63,15 tok/s TG
Prefill 1.472 · TTFT 1.659 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
19gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
51,11 tok/s TG
Prefill 899 · TTFT 2.279 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
20gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
48,95 tok/s TG
Prefill 919 · TTFT 2.243 ms
1×NVIDIA RTX SPARK (N1X)NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) · 128 GB RAMllama.cppopenclaw_cliMXFP4Details →
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU).

In the leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← All hardware

Technische Daten

Technische Daten – NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU)

HerstellerIntel
Best generation200,5 tok/s
Best prefill5.833 tok/s
Models5
Messläufe (Performance)20