mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

Global Score

69 vs 83

Hardware Fit

50 vs 100

Quality Score

77 vs 76

Hardware

mistralai/devstral… qwen3.5:4b

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… qwen3.5:4b

Tokens/sec5.732.4

First chunk5007 ms306 ms

TTFT5.0 s306 ms

Load timeN/A2.7 s

Memory usage13.2 GB6.5 GB

Memory %41%20%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

qwen3.5:4b

Speed

50/50

TTFT

20/20

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

qwen3.5:4b

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

View mistralai/devstral… details | View qwen3.5:4b 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