Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 752.39M · Q8_0

Not Rec.

Oct 11, 2026 · AMD Ryzen 5 5500

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score
44 vs 66
Hardware Fit
80 vs 23
Quality Score
28 vs 84

Hardware

qwen3.5:0.8b GPT-120B:120b
MachineMicrosoft WSLHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUAMD Ryzen 5 5500NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1220
RAM8 GB55 GB
GPUIntegrated / UnknownNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:0.8b GPT-120B:120b
Tokens/sec126.116.8
First chunk64 ms11247 ms
TTFT30.0 s12.2 s
Load time0.0 s77.3 s
Memory usage0.5 GB61.6 GB
Memory %7%113%

HW Fit Score Breakdown

qwen3.5:0.8b

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

GPT-120B:120b

Speed
21/50
TTFT
2/20
Memory
0/30

Quality

qwen3.5:0.8b

Reasoning
9/20
Coding
0/20
Instruction
7/20
Structured
1/15
Math
6/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Adequate

GPT-120B:120b

Reasoning
16/20
Coding
19/20
Instruction
11/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:0.8b details | View GPT-120B:120b 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