Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 25, 2026 · Intel Core™ Ultra X7 358H

Global Score
66 vs 68
Hardware Fit
40 vs 21
Quality Score
77 vs 88

Hardware

gemma4:31b GPT-120B:120b
MachineASUSTeK COMPUTER INC. GX10GMKtec NucBox EVO-T2S
CPUCortex-X925Intel Core™ Ultra X7 358H
Cores2016
RAM122 GB64 GB
GPUDevice 2e12Intel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

gemma4:31b GPT-120B:120b
Tokens/sec10.712.1
First chunk983 ms4392 ms
TTFT20.3 s8.7 s
Load time8.8 s80.1 s
Memory usage21.4 GB61.0 GB
Memory %18%96%

HW Fit Score Breakdown

gemma4:31b

Speed
10/50
TTFT
0/20
Memory
30/30

GPT-120B:120b

Speed
15/50
TTFT
4/20
Memory
2/30

Quality

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

GPT-120B:120b

Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
Math
15/15
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