mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

huihui_ai/Qwen3.8-abliterated:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 25, 2026 · AMD RYZEN AI MAX+ 395

Global Score

69 vs 80

Hardware Fit

50 vs 65

Quality Score

77 vs 87

Hardware

mistralai/devstral… huihui_ai/Qwen3.8-…

MachineMacBook AirAZW GTR Pro

CPUApple M4AMD RYZEN AI MAX+ 395

Cores1032

RAM32 GB125 GB

GPUApple M4Radeon 8060S

OSmacOS 26.3Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedlow-power

Performance

mistralai/devstral… huihui_ai/Qwen3.8-…

Tokens/sec5.717.5

First chunk5007 ms597 ms

TTFT5.0 s597 ms

Load timeN/A7.1 s

Memory usage13.2 GB17.4 GB

Memory %41%14%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

huihui_ai/Qwen3.8-ablit…

Speed

16/50

TTFT

19/20

Memory

30/30

Quality

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

huihui_ai/Qwen3.8-ablit…

Reasoning

17/20

Coding

18/20

Instruction

16/20

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 huihui_ai/Qwen3.8-… 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