Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 19, 2026 · Intel Core™ Ultra X7 358H

Global Score
29 vs 67
Hardware Fit
86 vs 21
Quality Score
4 vs 87

Hardware

qwen3:4b GPT-120B:120b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperGMKtec NucBox EVO-T2S
CPUCortex-A78AEIntel Core™ Ultra X7 358H
Cores616
RAM7 GB64 GB
GPUIntegrated / UnknownIntel(R) Arc(TM) B390 GPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3:4b GPT-120B:120b
Tokens/sec17.911.8
First chunk1010 ms4674 ms
TTFT6.4 s9.3 s
Load time9.5 s77.6 s
Memory usage3.0 GB61.0 GB
Memory %40%96%

HW Fit Score Breakdown

qwen3:4b

Speed
50/50
TTFT
8/20
Memory
28/30

GPT-120B:120b

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

Quality

qwen3:4b

Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

GPT-120B:120b

Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
14/15
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