mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score

69 vs 53

Hardware Fit

50 vs 72

Quality Score

77 vs 45

Hardware

mistralai/devstral… qwen3.5:9b

MachineMacBook AirMacBook Pro

CPUApple M4Apple M1 Max

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M1 Max

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3.5:9b

Tokens/sec5.718.6

First chunk5007 ms403 ms

TTFT5.0 s10.2 s

Load timeN/A4.3 s

Memory usage13.2 GB9.1 GB

Memory %41%28%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

qwen3.5:9b

Speed

38/50

TTFT

4/20

Memory

30/30

Quality

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

qwen3.5:9b

Reasoning

12/20

Coding

3/20

Instruction

5/20

Structured

6/15

Math

11/15

Multilingual

8/10

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

View mistralai/devstral… details | View qwen3.5:9b 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