Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Good

Aug 18, 2026 · Intel Xeon® E5-2637 v3

Global Score
76 vs 78
Hardware Fit
46 vs 51
Quality Score
89 vs 89

Hardware

gemma4:31b qwen3-next:80b-a3b…
MachineMacBook ProDell Inc. Precision Tower 7910
CPUApple M4 MaxIntel Xeon® E5-2637 v3
Cores1616
RAM64 GB96 GB
GPUApple M4 MaxNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSmacOS 26.3.1Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:31b qwen3-next:80b-a3b…
Tokens/sec22.48.7
First chunk565 ms1251 ms
TTFT30.0 s1.3 s
Load time6.9 s61.6 s
Memory usage43.9 GB48.3 GB
Memory %69%50%

HW Fit Score Breakdown

gemma4:31b

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

qwen3-next:80b-a3b-inst…

Speed
9/50
TTFT
17/20
Memory
25/30

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-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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