Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

gpt-oss:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Excellent

Oct 2, 2026 · Cortex-X925

Global Score
50 vs 83
Hardware Fit
93 vs 64
Quality Score
31 vs 91

Hardware

qwen3.5:4b gpt-oss:120b
MachineMicrosoft WSLNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 5 5500Cortex-X925
Cores1220
RAM8 GB122 GB
GPUIntegrated / UnknownDevice 2e12
OSUbuntu 26.04.1 LTSUbuntu 24.04.5 LTS
Archx64arm64
Power Modeunknownperformance

Performance

qwen3.5:4b gpt-oss:120b
Tokens/sec92.628.6
First chunk323 ms422 ms
TTFT2.8 s2.5 s
Load time9.0 s9.9 s
Memory usage2.9 GB60.1 GB
Memory %38%49%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
15/20
Memory
28/30

gpt-oss:120b

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

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
12/15
Multilingual
0/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

gpt-oss:120b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b details | View gpt-oss: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