Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
76 vs 82
Hardware Fit
46 vs 93
Quality Score
89 vs 77

Hardware

gemma4:31b qwen3.5:4b
MachineMacBook ProAZW GTR Pro
CPUApple M4 MaxAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1632
RAM64 GB125 GB
GPUApple M4 MaxIntegrated / Apple Silicon
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

gemma4:31b qwen3.5:4b
Tokens/sec22.446.8
First chunk565 ms174 ms
TTFT30.0 s174 ms
Load time6.9 s5.9 s
Memory usage43.9 GB16.2 GB
Memory %69%13%

HW Fit Score Breakdown

gemma4:31b

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

qwen3.5:4b

Speed
43/50
TTFT
20/20
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

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma4:31b 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