Created bymario-alka.dePowered bynoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Contributed byMario AlkaMistral AI

Mamba-Codestral-7B-v0.1

Performance benchmark · measured on 12.11.2026 15:35

Benchmark-IDrun-20261112-144801-d46ed4
Timebench 3 - Kombi (Prefill + Generation)Dense7BRuntime: lmstudio-mlxQuantisierung: MLX 4bit
Generation29,25tok/s
Prefill327,36tok/s
Time to First Token8.424,30ms
Total duration134,79s
Concurrency1parallel
Ranking in the field
This GPUAll GPUs
1276of 1927 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 34 % of all comparable systems.
Generation 29,3 tok/s
-62 % vs Ø 77,5
Prefill 327,4 tok/s
-88 % vs Ø 2.844,6
Time to First Token 8.424 ms
-65 % vs Ø 23.755
Distribution in the field0 – 471 tok/s
Ø 78 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

Hardware

GPU: Keine GPU (CPU-only)
CPU: Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD)
RAM: 24 GB
Mainboard: Apple Mac mini

Setup

Runtime: lmstudio-mlx
Quantization: MLX 4bit
Model: Mamba-Codestral-7B-v0.1

Configuration

benchmark-konfiguration — run-20261112-144801-d46ed4
# LLM-Benchmark Konfiguration # Modell : Mamba-Codestral-7B-v0.1 # Engine : lmstudio-mlx # Run-ID : run-20261112-144801-d46ed4 # GPU : Keine GPU (CPU-only) # CPU : Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) # RAM : 24 GB bench@llm-benchmark:~$ lmstudio-mlx \ --model mamba-codestral-7b-v0.1
Engine?Die Inferenz-Software, die das Modell ausliefert (z.B. vLLM oder llama.cpp). Sie bestimmt Geschwindigkeit, unterstuetzte Modellformate und welche Parameter ueberhaupt verfuegbar sind.lmstudio-mlx
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.8192
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Mamba-Codestral-7B-v0.1 on various hardware

All published performance runs of this model – each bubble a variant: position = prefill (X) × generation (Y), bubble size = number of runs. Closer to the top right = faster. ★ Marked gold = this benchmark.

GPUby graphics card

32,230,729,327,826,3308321334347Prefill (tok/s)Generation (tok/s)CPU-only - 29,3 tok/s Generation, 327 tok/s Prefill, TTFT 8.424 ms (1 Lauf) | DIESER LAUF★ CPU-only
★ CPU-only 29,3 tok/s this run

CPUby processor

32,230,729,327,826,3308321334347Prefill (tok/s)Generation (tok/s)Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) - 29,3 tok/s Generation, 327 tok/s Prefill, TTFT 8.424 ms (1 Lauf) | DIESER LAUF★ Apple M6 (unified CPU...
★ Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) 29,3 tok/s this run

MBby mainboard

32,230,729,327,826,3308321334347Prefill (tok/s)Generation (tok/s)Apple Mac mini - 29,3 tok/s Generation, 327 tok/s Prefill, TTFT 8.424 ms (1 Lauf) | DIESER LAUF★ Apple Mac mini
★ Apple Mac mini 29,3 tok/s this run

ENGby engine

32,230,729,327,826,3308321334347Prefill (tok/s)Generation (tok/s)lmstudio-mlx - 29,3 tok/s Generation, 327 tok/s Prefill, TTFT 8.424 ms (1 Lauf) | DIESER LAUF★ lmstudio-mlx
★ lmstudio-mlx 29,3 tok/s this run

DRVby driver

32,230,729,327,826,3308321334347Prefill (tok/s)Generation (tok/s)unbekannt - 29,3 tok/s Generation, 327 tok/s Prefill, TTFT 8.424 ms (1 Lauf)unbekannt
unbekannt 29,3 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× concurrent). Methodology →

⚙️ ConfigurationAll metrics and charts below follow these settings – based on a 24-month runtime.Save to URLReset
⚡ Electricity price EUR/kWh
⚙️ System utilization 100 %
🔌 Idle 0 W
⚡ TDP 10 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)0 W missing
Avg cost / hour–
Electricity / 1M tokens–
Token / kWh–
Acquisition (system)– partial price
Electricity (2 years)–
TCO (2 years)–
Output tokens (2 years)1.84B
☁️ External LLM (API) – comparison
External LLM cost (2 years)–
Savings vs. external (2 years)–
No power draw measured – values estimated from GPU TDP + CPU (idle + 15 %) + board.

All values above and the charts below take the configured system utilization into account: at X% the system generates only X% of the time, the rest it idles (0 W). Cost per hour drops (more idle), cost per token rises.

Cost over 2 years – electricity only

Cost over 2 years – incl. acquisition (TCO)

Speed vs. tokens per euro

Euro per 1M tokens

Comparison vs. API – economics per benchmark

Mamba-Codestral-7B-v0.1Keine GPU (CPU-only)
Electricity cost (24 mo.)–
Acquisition cost–
Total cost (TCO)–
Generated tokens (24 mo.)–
Token price via API–
Break-even point (days)–
Result (savings / extra cost)–
Keine GPU (CPU-only) · this run 29 tok/s

Comparison with up to 3 next-best runs of this model at the same concurrency (at least one on different hardware). Power = GPU TDP + CPU (idle + 15 %) + board (estimated), acquisition = full system (GPU + CPU + board + RAM + PSU), prices = stored market prices.

Contributed by

Mario Alka Administrator

@marioalka

Ich bin Unternehmer, Softwareentwickler und KI-Enthusiast. Seit vielen Jahren entwickle ich Unternehmenssoftware und beschäftige mich inzwischen fast täglich mit lokalen LLMs, KI-Agenten und leistungsfähiger KI-Hardware.

Mit LLM-Benchmark.de möchte ich eine Plattform schaffen, auf der Modelle, GPUs und Agenten objektiv und reproduzierbar miteinander verglichen werden.