qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score

83 vs 73

Hardware Fit

100 vs 64

Quality Score

76 vs 77

Hardware

qwen3.5:4b mistralai/devstral…

MachineMacBook ProMacBook Pro

CPUApple M1 MaxApple M1 Pro

Cores1010

RAM32 GB32 GB

GPUApple M1 MaxApple M1 Pro

OSmacOS 26.3macOS 15.6.1

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:4b mistralai/devstral…

Tokens/sec32.411.9

First chunk306 ms7 ms

TTFT306 ms1.1 s

Load time2.7 sN/A

Memory usage6.5 GB19.7 GB

Memory %20%62%

HW Fit Score Breakdown

qwen3.5:4b

Speed

50/50

TTFT

20/20

Memory

30/30

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

Quality

qwen3.5:4b

Reasoning

16/20

Coding

14/20

Instruction

15/20

Structured

15/15

Math

7/15

Multilingual

9/10

Reasoning: Strong Coding: Adequate 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 qwen3.5:4b 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