mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Xeon® E5-2637 v3

Global Score

73 vs 81

Hardware Fit

64 vs 72

Quality Score

77 vs 85

Hardware

mistralai/devstral… qwen3.5:35b-a3b-q4…

MachineMacBook ProDell Inc. Precision Tower 7910

CPUApple M1 ProIntel Xeon® E5-2637 v3

Cores1016

RAM32 GB96 GB

GPUApple M1 ProNVIDIA GeForce RTX 5060 Ti

OSmacOS 15.6.1Microsoft Windows 10 Pro 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3.5:35b-a3b-q4…

Tokens/sec11.924.2

First chunk7 ms1607 ms

TTFT1.1 s1.6 s

Load timeN/A66.4 s

Memory usage19.7 GB22.7 GB

Memory %62%24%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

qwen3.5:35b-a3b-q4_K_M

Speed

28/50

TTFT

14/20

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

qwen3.5:35b-a3b-q4_K_M

Reasoning

16/20

Coding

18/20

Instruction

15/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

View mistralai/devstral… details | View qwen3.5:35b-a3b-q4… 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