mistralai/magistral-small-2509

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

mlx-community/quantized-gemma-2b-it

LM-STUDIO GGUF

Marginal

Mar 5, 2026 · Apple M4

Global Score

74 vs 45

Hardware Fit

66 vs 100

Quality Score

78 vs 21

Hardware

mistralai/magistra… mlx-community/quan…

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/magistra… mlx-community/quan…

Tokens/sec7.944.4

First chunk1356 ms336 ms

TTFT1.4 s336 ms

Load timeN/AN/A

Memory usage13.2 GB0.1 GB

Memory %41%0%

HW Fit Score Breakdown

mistralai/magistral-sma…

Speed

16/50

TTFT

20/20

Memory

30/30

mlx-community/quantized…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

mistralai/magistral-sma…

Reasoning

14/20

Coding

18/20

Instruction

14/20

Structured

15/15

Math

7/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

mlx-community/quantized…

Reasoning

4/20

Coding

1/20

Instruction

9/20

Structured

4/15

Math

2/15

Multilingual

1/10

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

View mistralai/magistra… details | View mlx-community/quan… details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest