mistralai/magistral-small-2509

mistral3 · 24B · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 3, 2026

Top 100% Compare

Global Score

20 /100

Not Rec.

Hardware Fit

65/100

Quality

0/100

Get this model

🦙

Ollama

ollama pull mistralai/magistral-small-2509

View on Ollama Library

ollama.com/library/mistralai/magistral-small-2509

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 5.1
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
Time to first token How fast the model starts responding — lower is better: 2.0 s
Load time Time to load the model into memory before inference: 0.0 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.0 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 1956

Score breakdown

Speed

8/40

Time to first token

27/30

Memory

30/30

Quality

Reasoning

0/20

Coding

0/20

Instruction following

0/20

Structured output

0/15

Math

0/15

Multilingual

0/10

Category levels

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

Metadata

Spec version: 0.2.0
Runtime: Lm-studio unknown
Model format: GGUF
Hardware profile: BALANCED
Result hash: 215cea644dfe9180e0762902aff6ded1894da955a3ee589acd4dd5f35c869e4d

Interpretation

Hardware fit: 65/100. Overall suitability: NOT RECOMMENDED (Global 20/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Poor, Multilingual: Poor. Warning: model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.

Warnings

Model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running