mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M

OLLAMA GGUF

qwen35 · 4.33B · unknown

Good

Aug 28, 2026 · Apple M4

Global Score

73 vs 66

Hardware Fit

64 vs 100

Quality Score

77 vs 52

Hardware

mistralai/devstral… hf.co/empero-ai/Qw…

MachineMacBook ProMacBook Pro

CPUApple M1 ProApple M4

Cores1010

RAM32 GB16 GB

GPUApple M1 ProApple M4

OSmacOS 15.6.1macOS 26.6.1

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/devstral… hf.co/empero-ai/Qw…

Tokens/sec11.926.5

First chunk7 ms447 ms

TTFT1.1 s447 ms

Load timeN/A3.3 s

Memory usage19.7 GB4.8 GB

Memory %62%30%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

hf.co/empero-ai/Qwen3.8…

Speed

50/50

TTFT

20/20

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

hf.co/empero-ai/Qwen3.8…

Reasoning

18/20

Coding

14/20

Instruction

4/20

Structured

1/15

Math

15/15

Multilingual

0/10

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

View mistralai/devstral… details | View hf.co/empero-ai/Qw… 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