Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.5:122b-a10b

OLLAMA GGUF

qwen35moe · 125.1B · Q4_K_M

Excellent

Mar 12, 2026 · AMD RYZEN AI MAX+ 395

Global Score
76 vs 80
Hardware Fit
46 vs 52
Quality Score
89 vs 92

Hardware

gemma4:31b qwen3.5:122b-a10b
MachineMacBook ProAZW GTR Pro
CPUApple M4 MaxAMD RYZEN AI MAX+ 395
Cores1632
RAM64 GB125 GB
GPUApple M4 MaxRadeon 8060S
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

gemma4:31b qwen3.5:122b-a10b
Tokens/sec22.419.1
First chunk565 ms467 ms
TTFT30.0 s467 ms
Load time6.9 s30.0 s
Memory usage43.9 GB89.3 GB
Memory %69%72%

HW Fit Score Breakdown

gemma4:31b

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

qwen3.5:122b-a10b

Speed
18/50
TTFT
20/20
Memory
14/30

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

qwen3.5:122b-a10b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:31b details | View qwen3.5:122b-a10b 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