Back to leaderboard

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
73 vs 84
Hardware Fit
64 vs 69
Quality Score
77 vs 90

Hardware

mistralai/devstral… qwen/qwen3.8-27b
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M4 Max
Cores1016
RAM32 GB128 GB
GPUApple M1 ProApple M4 Max
OSmacOS 15.6.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

mistralai/devstral… qwen/qwen3.8-27b
Tokens/sec11.928.9
First chunk7 ms33 ms
TTFT1.1 s4.4 s
Load timeN/A7.9 s
Memory usage19.7 GB0.0 GB
Memory %62%0%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed
25/50
TTFT
20/20
Memory
19/30

qwen/qwen3.8-27b

Speed
33/50
TTFT
6/20
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

qwen/qwen3.8-27b

Reasoning
19/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View mistralai/devstral… details | View qwen/qwen3.8-27b 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