openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Sep 29, 2026 · Apple M5 Max
qwen3-4b-qwen3.6-plus-reasoning-distilled
LM-STUDIO GGUFqwen3 · 4B · Q4_1
Apr 21, 2026 · Apple M2 Max
Global Score
83 vs 65
Hardware Fit
80 vs 96
Quality Score
84 vs 51
Hardware
openai/gpt-oss-20b qwen3-4b-qwen3.6-p…
MachineMacBook ProMac Studio
CPUApple M5 MaxApple M2 Max
Cores1812
RAM128 GB96 GB
GPUApple M5 MaxApple M2 Max
OSmacOS 26.6.2macOS 26.1
Archarm64arm64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b qwen3-4b-qwen3.6-p…
Tokens/sec138.499.6
First chunk3 ms18 ms
TTFT30.0 s1.6 s
Load time6.8 s4.8 s
Memory usage0.5 GB0.3 GB
Memory %0%0%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3-4b-qwen3.6-plus-r…
Speed
50/50
TTFT
16/20
Memory
30/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
12/20
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
qwen3-4b-qwen3.6-plus-r…
Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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