Back to leaderboard

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 19, 2026 · Apple M4

Global Score
73 vs 66
Hardware Fit
64 vs 34
Quality Score
77 vs 79

Hardware

mistralai/devstral… qwen3.5:27b
MachineMacBook ProMac mini
CPUApple M1 ProApple M4
Cores1010
RAM32 GB24 GB
GPUApple M1 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3.5:27b
Tokens/sec11.93.8
First chunk7 ms1637 ms
TTFT1.1 s1.6 s
Load timeN/A17.0 s
Memory usage19.7 GB21.3 GB
Memory %62%89%

HW Fit Score Breakdown

mistralai/devstral-smal…

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

qwen3.5:27b

Speed
8/50
TTFT
20/20
Memory
6/30

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

qwen3.5:27b

Reasoning
16/20
Coding
18/20
Instruction
8/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
View mistralai/devstral… details | View qwen3.5:27b 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