Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Not Rec.

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex-mtp

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
84 vs 89
Hardware Fit
65 vs 90
Quality Score
92 vs 88

Hardware

openai/gpt-oss-20b qwen3.6-35b-a3b-cl…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM31 GB47 GB
GPUNVIDIA GeForce RTX 4090, RaphaelAD106 [GeForce RTX 4060 Ti]
OScachyos rollingcachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

openai/gpt-oss-20b qwen3.6-35b-a3b-cl…
Tokens/sec221.542.2
First chunk5 ms40 ms
TTFT30.0 s2.7 s
Load timeN/AN/A
Memory usage21.1 GB21.9 GB
Memory %69%47%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
0/20
Memory
15/30

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
14/20
Memory
26/30

Quality

openai/gpt-oss-20b

Reasoning
19/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.6-35b-a3b-claude-…

Reasoning
19/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View openai/gpt-oss-20b details | View qwen3.6-35b-a3b-cl… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest