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

LM-STUDIO GGUF

Excellent

Mar 5, 2026 · Apple M4

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score

80 vs 73

Hardware Fit

100 vs 64

Quality Score

71 vs 77

Hardware

mlx-community/gemm… mistralai/devstral…

MachineMacBook AirMacBook Pro

CPUApple M4Apple M1 Pro

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M1 Pro

OSmacOS 26.3macOS 15.6.1

Archarm64arm64

Power Modebalancedbalanced

Performance

mlx-community/gemm… mistralai/devstral…

Tokens/sec43.211.9

First chunk428 ms7 ms

TTFT428 ms1.1 s

Load timeN/AN/A

Memory usage1.3 GB19.7 GB

Memory %4%62%

HW Fit Score Breakdown

mlx-community/gemma-3-4…

Speed

50/50

TTFT

20/20

Memory

30/30

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

Quality

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

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

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