Back to leaderboard

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

gemma4:12b-it-qat

OLLAMA GGUF

gemma4 · 11.9B · Q4_0

Excellent

Jun 25, 2026 · Apple M4 Pro

Global Score
73 vs 88
Hardware Fit
64 vs 86
Quality Score
77 vs 89

Hardware

mistralai/devstral… gemma4:12b-it-qat
MachineMacBook ProMac mini
CPUApple M1 ProApple M4 Pro
Cores1012
RAM32 GB24 GB
GPUApple M1 ProApple M4 Pro
OSmacOS 15.6.1macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

mistralai/devstral… gemma4:12b-it-qat
Tokens/sec11.930.0
First chunk7 ms686 ms
TTFT1.1 s7.1 s
Load timeN/A5.4 s
Memory usage19.7 GB7.1 GB
Memory %62%30%

HW Fit Score Breakdown

mistralai/devstral-smal…

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

gemma4:12b-it-qat

Speed
50/50
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

gemma4:12b-it-qat

Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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