openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Jul 17, 2026 · Apple M5 Max
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
83 vs 61
Hardware Fit
80 vs 85
Quality Score
84 vs 51
Hardware
openai/gpt-oss-20b qwen3:0.6b
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M5 MaxIntel Core™ i5-8350U
Cores188
RAM64 GB23 GB
GPUApple M5 MaxKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 27.0Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power
Performance
openai/gpt-oss-20b qwen3:0.6b
Tokens/sec131.727.0
First chunk7 ms597 ms
TTFT30.0 s8.7 s
Load timeN/A1.8 s
Memory usage15.8 GB0.9 GB
Memory %25%4%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
13/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
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