qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

53 vs 69

Hardware Fit

82 vs 50

Quality Score

41 vs 77

Hardware

qwen3.5:4b-mlx mistralai/devstral…

MachineMac miniMacBook Air

CPUApple M2Apple M4

Cores810

RAM8 GB32 GB

GPUApple M2Apple M4

OSmacOS 26.5.2macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx mistralai/devstral…

Tokens/sec24.75.7

First chunk302 ms5007 ms

TTFT7.4 s5.0 s

Load time3.2 sN/A

Memory usage3.8 GB13.2 GB

Memory %47%41%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed

50/50

TTFT

6/20

Memory

26/30

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

Quality

qwen3.5:4b-mlx

Reasoning

13/20

Coding

2/20

Instruction

4/20

Structured

4/15

Math

10/15

Multilingual

8/10

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

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

View qwen3.5:4b-mlx 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