Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Not Rec.

Aug 19, 2026 · Apple M4 Max

Global Score
76 vs 88
Hardware Fit
46 vs 80
Quality Score
89 vs 92

Hardware

gemma4:31b qwen3.6-35b-a3b-cl…
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M4 Max
Cores1616
RAM64 GB128 GB
GPUApple M4 MaxApple M4 Max
OSmacOS 26.3.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:31b qwen3.6-35b-a3b-cl…
Tokens/sec22.476.7
First chunk565 ms29 ms
TTFT30.0 s30.0 s
Load time6.9 sN/A
Memory usage43.9 GB23.9 GB
Memory %69%19%

HW Fit Score Breakdown

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

gemma4:31b

Reasoning
16/20
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

qwen3.6-35b-a3b-claude-…

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:31b details | View qwen3.6-35b-a3b-cl… 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