Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score
76 vs 53
Hardware Fit
46 vs 72
Quality Score
89 vs 45

Hardware

gemma4:31b qwen3.5:9b
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M1 Max
Cores1610
RAM64 GB32 GB
GPUApple M4 MaxApple M1 Max
OSmacOS 26.3.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:31b qwen3.5:9b
Tokens/sec22.418.6
First chunk565 ms403 ms
TTFT30.0 s10.2 s
Load time6.9 s4.3 s
Memory usage43.9 GB9.1 GB
Memory %69%28%

HW Fit Score Breakdown

gemma4:31b

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

qwen3.5:9b

Speed
38/50
TTFT
4/20
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

qwen3.5:9b

Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
View gemma4:31b details | View qwen3.5:9b 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