mistralai/magistral-small-2509

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

mlx-community/gemma-3-4b-it-qat-4bit

LM-STUDIO GGUF

Excellent

Mar 5, 2026 · Apple M4

Global Score

74 vs 80

Hardware Fit

66 vs 100

Quality Score

78 vs 71

Hardware

mistralai/magistra… mlx-community/gemm…

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/gemm…

Tokens/sec7.943.2

First chunk1356 ms428 ms

TTFT1.4 s428 ms

Load timeN/AN/A

Memory usage13.2 GB1.3 GB

Memory %41%4%

HW Fit Score Breakdown

mistralai/magistral-sma…

Speed

16/50

TTFT

20/20

Memory

30/30

mlx-community/gemma-3-4…

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/gemma-3-4…

Reasoning

9/20

Coding

17/20

Instruction

17/20

Structured

13/15

Math

5/15

Multilingual

10/10

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

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