Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
76 vs 20
Hardware Fit
46 vs 37
Quality Score
89 vs 12

Hardware

gemma4:31b qwen3.5:27b
MachineMacBook ProAZW GTR Pro
CPUApple M4 MaxAMD RYZEN AI MAX+ 395
Cores1632
RAM64 GB125 GB
GPUApple M4 MaxAMD Radeon 8060S
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

gemma4:31b qwen3.5:27b
Tokens/sec22.410.6
First chunk565 ms358 ms
TTFT30.0 s13.7 s
Load time6.9 s10.8 s
Memory usage43.9 GB39.7 GB
Memory %69%32%

HW Fit Score Breakdown

gemma4:31b

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

qwen3.5:27b

Speed
9/50
TTFT
0/20
Memory
28/30

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

qwen3.5:27b

Reasoning
2/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor 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