Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen/qwen3.6-35b-a3b:2

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
76 vs 73
Hardware Fit
46 vs 50
Quality Score
89 vs 83

Hardware

gemma4:31b qwen/qwen3.6-35b-a…
MachineMacBook ProSystem manufacturer
CPUApple M4 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM64 GB31 GB
GPUApple M4 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.3.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

gemma4:31b qwen/qwen3.6-35b-a…
Tokens/sec22.410.5
First chunk565 ms4 ms
TTFT30.0 s1.7 s
Load time6.9 sN/A
Memory usage43.9 GB21.4 GB
Memory %69%69%

HW Fit Score Breakdown

gemma4:31b

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

qwen/qwen3.6-35b-a3b:2

Speed
16/50
TTFT
18/20
Memory
16/30

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

qwen/qwen3.6-35b-a3b:2

Reasoning
16/20
Coding
15/20
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 qwen/qwen3.6-35b-a… 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