openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Global Score
91 vs 82
Hardware Fit
90 vs 93
Quality Score
91 vs 77
Hardware
openai/gpt-oss-20b qwen3.5:4b
MachineMacBook ProAZW GTR Pro
CPUApple M3 MaxAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1632
RAM128 GB125 GB
GPUApple M3 MaxIntegrated / Apple Silicon
OSmacOS 27.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
openai/gpt-oss-20b qwen3.5:4b
Tokens/sec95.146.8
First chunk3 ms174 ms
TTFT2.5 s174 ms
Load time9.2 s5.9 s
Memory usage0.0 GB16.2 GB
Memory %0%13%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
qwen3.5:4b
Speed
43/50
TTFT
20/20
Memory
30/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5:4b
Reasoning
15/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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