qwen3.5:0.8b
OLLAMA GGUFqwen35 · 752.39M · Q8_0
Oct 11, 2026 · AMD Ryzen 5 5500
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
Global Score
44 vs 87
Hardware Fit
80 vs 83
Quality Score
28 vs 88
Hardware
qwen3.5:0.8b gpt-oss:20b
MachineMicrosoft WSLMac mini
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM8 GB24 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modeunknownbalanced
Performance
qwen3.5:0.8b gpt-oss:20b
Tokens/sec126.124.3
First chunk64 ms529 ms
TTFT30.0 s4.5 s
Load time0.0 s11.2 s
Memory usage0.5 GB13.1 GB
Memory %7%55%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
50/50
TTFT
0/20
Memory
30/30
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
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-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
11/20
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