mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

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

LM-STUDIO GGUF

Excellent

Mar 5, 2026 · Apple M4

Global Score

73 vs 80

Hardware Fit

64 vs 100

Quality Score

77 vs 71

Hardware

mistralai/devstral… mlx-community/gemm…

MachineMacBook ProMacBook Air

CPUApple M1 ProApple M4

Cores1010

RAM32 GB32 GB

GPUApple M1 ProApple M4

OSmacOS 15.6.1macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/devstral… mlx-community/gemm…

Tokens/sec11.943.2

First chunk7 ms428 ms

TTFT1.1 s428 ms

Load timeN/AN/A

Memory usage19.7 GB1.3 GB

Memory %62%4%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

mlx-community/gemma-3-4…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

mistralai/devstral-smal…

Reasoning

17/20

Coding

16/20

Instruction

13/20

Structured

14/15

Math

7/15

Multilingual

10/10

Reasoning: Strong 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/devstral… 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