qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
61 vs 67
Hardware Fit
69 vs 21
Quality Score
58 vs 87
Hardware
qwen3.5:4b GPT-120B:120b
MachineGigabyte Technology Co., Ltd. H170M-D3HGMKtec NucBox EVO-T2S
CPUIntel Core™ i5-6500Intel Core™ Ultra X7 358H
Cores416
RAM16 GB64 GB
GPUGP104 [GeForce GTX 1070]Intel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
qwen3.5:4b GPT-120B:120b
Tokens/sec35.711.8
First chunk438 ms4674 ms
TTFT5.1 s9.3 s
Load time40.1 s77.6 s
Memory usage5.5 GB61.0 GB
Memory %35%96%
HW Fit Score Breakdown
qwen3.5:4b
Speed
50/50
TTFT
11/20
Memory
8/30
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
qwen3.5:4b
Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest