gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
83 vs 18
Hardware Fit
65 vs 53
Quality Score
90 vs 3
Hardware
gpt-oss:20b qwen3.5:0.8b
MachineMac miniLENOVO 20L7CTO1WW
CPUApple M4Intel Core™ i5-8350U
Cores108
RAM24 GB23 GB
GPUApple M4Kaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.3Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power
Performance
gpt-oss:20b qwen3.5:0.8b
Tokens/sec17.19.4
First chunk705 ms799 ms
TTFT10.2 s30.0 s
Load time23.1 s3.3 s
Memory usage13.1 GB1.9 GB
Memory %55%8%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
qwen3.5:0.8b
Speed
23/50
TTFT
0/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5:0.8b
Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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