Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
76 vs 79
Hardware Fit
46 vs 59
Quality Score
89 vs 87

Hardware

gemma4:31b qwen3.6-35b-a3b
MachineMacBook ProDocker Container
CPUApple M4 MaxIntel Gen Intel® Core™ i9-11900H
Cores1616
RAM64 GB15 GB
GPUApple M4 MaxTigerLake-H GT1 [UHD Graphics]
OSmacOS 26.3.1Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

gemma4:31b qwen3.6-35b-a3b
Tokens/sec22.49.3
First chunk565 ms21 ms
TTFT30.0 s3.6 s
Load time6.9 s32.0 s
Memory usage43.9 GB1.8 GB
Memory %69%12%

HW Fit Score Breakdown

gemma4:31b

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

qwen3.6-35b-a3b

Speed
17/50
TTFT
12/20
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

qwen3.6-35b-a3b

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 qwen3.6-35b-a3b 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