Back to leaderboard

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 23, 2026 · Apple M1 Pro

Global Score
73 vs 69
Hardware Fit
64 vs 86
Quality Score
77 vs 62

Hardware

mistralai/devstral… qwen3.5:4b
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M1 ProApple M1 Pro
OSmacOS 15.6.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3.5:4b
Tokens/sec11.936.7
First chunk7 ms207 ms
TTFT1.1 s6.6 s
Load timeN/A3.0 s
Memory usage19.7 GB5.3 GB
Memory %62%33%

HW Fit Score Breakdown

mistralai/devstral-smal…

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

qwen3.5:4b

Speed
50/50
TTFT
7/20
Memory
29/30

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

qwen3.5:4b

Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong
View mistralai/devstral… details | View qwen3.5:4b 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