gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
83 vs 88
Hardware Fit
65 vs 85
Quality Score
90 vs 89
Hardware
gpt-oss:20b huihui-qwen3.6-35b…
MachineMac miniGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4AMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM24 GB47 GB
GPUApple M4AD106 [GeForce RTX 4060 Ti]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
gpt-oss:20b huihui-qwen3.6-35b…
Tokens/sec17.137.7
First chunk705 ms18 ms
TTFT10.2 s2.9 s
Load time23.1 sN/A
Memory usage13.1 GB26.1 GB
Memory %55%56%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
13/20
Memory
22/30
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
huihui-qwen3.6-35b-a3b-…
Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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