openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Oct 20, 2026 · Apple M1 Pro
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
Global Score
83 vs 80
Hardware Fit
75 vs 85
Quality Score
87 vs 78
Hardware
openai/gpt-oss-20b qwen3:8b
MachineMacBook ProHP HP Z8 G4 Workstation
CPUApple M1 ProIntel Xeon® Gold 6230
Cores1080
RAM32 GB252 GB
GPUApple M1 ProTU104GL [Quadro RTX 5000]
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
openai/gpt-oss-20b qwen3:8b
Tokens/sec43.265.1
First chunk46 ms289 ms
TTFT30.0 s4.2 s
Load timeN/A4.6 s
Memory usage15.8 GB5.6 GB
Memory %49%2%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
25/30
qwen3:8b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
openai/gpt-oss-20b
Reasoning
19/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:8b
Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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