mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score

73 vs 66

Hardware Fit

64 vs 40

Quality Score

77 vs 77

Hardware

mistralai/devstral… gemma4:31b

MachineMacBook ProASUSTeK COMPUTER INC. GX10

CPUApple M1 ProCortex-X925

Cores1020

RAM32 GB122 GB

GPUApple M1 ProDevice 2e12

OSmacOS 15.6.1Ubuntu 24.04.4 LTS

Archarm64arm64

Power Modebalancedperformance

Performance

mistralai/devstral… gemma4:31b

Tokens/sec11.910.7

First chunk7 ms983 ms

TTFT1.1 s20.3 s

Load timeN/A8.8 s

Memory usage19.7 GB21.4 GB

Memory %62%18%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

gemma4:31b

Speed

10/50

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

gemma4:31b

Reasoning

14/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

10/15

Multilingual

9/10

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

View mistralai/devstral… details | View gemma4:31b 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