mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3-30b-a3b-t16-c32k-instruct:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 18, 2026 · Intel Xeon® E5-2637 v3

Global Score

73 vs 93

Hardware Fit

64 vs 97

Quality Score

77 vs 91

Hardware

mistralai/devstral… qwen3-30b-a3b-t16-…

MachineMacBook ProDell Inc. Precision Tower 7910

CPUApple M1 ProIntel Xeon® E5-2637 v3

Cores1016

RAM32 GB96 GB

GPUApple M1 ProNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060

OSmacOS 15.6.1Microsoft Windows 10 Pro 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3-30b-a3b-t16-…

Tokens/sec11.9100.0

First chunk7 ms1275 ms

TTFT1.1 s1.3 s

Load timeN/A23.6 s

Memory usage19.7 GB21.0 GB

Memory %62%22%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

qwen3-30b-a3b-t16-c32k-…

Speed

50/50

TTFT

17/20

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

qwen3-30b-a3b-t16-c32k-…

Reasoning

17/20

Coding

19/20

Instruction

16/20

Structured

15/15

Math

14/15

Multilingual

10/10

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

View mistralai/devstral… details | View qwen3-30b-a3b-t16-… 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