mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_S

Not Rec.

Apr 20, 2026 · Apple M2 Max

Global Score

73 vs 82

Hardware Fit

64 vs 80

Quality Score

77 vs 83

Hardware

mistralai/devstral… qwen3.6-35b-a3b

MachineMacBook ProMac Studio

CPUApple M1 ProApple M2 Max

Cores1012

RAM32 GB96 GB

GPUApple M1 ProApple M2 Max

OSmacOS 15.6.1macOS 26.1

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3.6-35b-a3b

Tokens/sec11.955.2

First chunk7 ms4 ms

TTFT1.1 s30.0 s

Load timeN/AN/A

Memory usage19.7 GB30.3 GB

Memory %62%32%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

qwen3.6-35b-a3b

Speed

50/50

TTFT

0/20

Memory

30/30

Quality

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

qwen3.6-35b-a3b

Reasoning

18/20

Coding

10/20

Instruction

18/20

Structured

14/15

Math

14/15

Multilingual

9/10

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

View mistralai/devstral… details | View qwen3.6-35b-a3b 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