Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

ministral-3:8b

OLLAMA GGUF

mistral3 · 8.9B · Q4_K_M

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
78 vs 72
Hardware Fit
47 vs 71
Quality Score
92 vs 72

Hardware

gemma4:31b ministral-3:8b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPURadeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced

Performance

gemma4:31b ministral-3:8b
Tokens/sec9.819.8
First chunk873 ms269 ms
TTFT873 ms269 ms
Load time7.0 s10.7 s
Memory usage68.3 GB13.7 GB
Memory %55%86%

HW Fit Score Breakdown

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

ministral-3:8b

Speed
44/50
TTFT
20/20
Memory
7/30

Quality

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

ministral-3:8b

Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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