GPT-OSS-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
unsloth/qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q3_K_M
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
93 vs 85
Hardware Fit
92 vs 79
Quality Score
93 vs 88
Hardware
GPT-OSS-20B:20b unsloth/qwen3.6-35…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCSystem manufacturer
CPUIntel Core™ i7-14700FAMD Ryzen 7 5800X 8-Core Processor
Cores2816
RAM128 GB31 GB
GPUNVIDIA GeForce RTX 5080Navi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedperformance
Performance
GPT-OSS-20B:20b unsloth/qwen3.6-35…
Tokens/sec178.623.5
First chunk695 ms54 ms
TTFT1.4 s457 ms
Load time31.2 sN/A
Memory usage11.9 GB18.3 GB
Memory %9%59%
HW Fit Score Breakdown
GPT-OSS-20B:20b
Speed
50/50
TTFT
12/20
Memory
30/30
unsloth/qwen3.6-35b-a3b
Speed
38/50
TTFT
20/20
Memory
21/30
Quality
GPT-OSS-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
unsloth/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
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