mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Qwen3.8-27B-Opus-Distill-IQ3_XXS:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ3_XXS

Good

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score

73 vs 73

Hardware Fit

64 vs 98

Quality Score

77 vs 62

Hardware

mistralai/devstral… Qwen3.8-27B-Opus-D…

MachineMacBook ProMicro-Star International Co., Ltd. MS-7E51

CPUApple M1 ProAMD Ryzen 7 9700X 8-Core Processor

Cores1016

RAM32 GB31 GB

GPUApple M1 ProNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics

OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

mistralai/devstral… Qwen3.8-27B-Opus-D…

Tokens/sec11.961.4

First chunk7 ms381 ms

TTFT1.1 s381 ms

Load timeN/A0.2 s

Memory usage19.7 GB12.2 GB

Memory %62%39%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

Qwen3.8-27B-Opus-Distil…

Speed

50/50

TTFT

20/20

Memory

28/30

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

Qwen3.8-27B-Opus-Distil…

Reasoning

17/20

Coding

18/20

Instruction

8/20

Structured

0/15

Math

13/15

Multilingual

6/10

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

View mistralai/devstral… details | View Qwen3.8-27B-Opus-D… 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