Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
76 vs 77
Hardware Fit
46 vs 53
Quality Score
89 vs 87

Hardware

gemma4:31b qwen3.5:35b
MachineMacBook ProASUS
CPUApple M4 MaxIntel Core™ i5-14600KF
Cores1620
RAM64 GB32 GB
GPUApple M4 MaxNVIDIA GeForce RTX 4070 Ti SUPER
OSmacOS 26.3.1Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:31b qwen3.5:35b
Tokens/sec22.416.0
First chunk565 ms719 ms
TTFT30.0 s719 ms
Load time6.9 s17.8 s
Memory usage43.9 GB25.0 GB
Memory %69%79%

HW Fit Score Breakdown

gemma4:31b

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

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

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

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:31b details | View qwen3.5:35b 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