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

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Xeon® E5-2637 v3

Global Score
84 vs 81
Hardware Fit
65 vs 72
Quality Score
92 vs 85

Hardware

openai/gpt-oss-20b qwen3.5:35b-a3b-q4…
MachineASUSDell Inc. Precision Tower 7910
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorIntel Xeon® E5-2637 v3
Cores1616
RAM31 GB96 GB
GPUNVIDIA GeForce RTX 4090, RaphaelNVIDIA GeForce RTX 5060 Ti
OScachyos rollingMicrosoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modeperformancebalanced

Performance

openai/gpt-oss-20b qwen3.5:35b-a3b-q4…
Tokens/sec221.524.2
First chunk5 ms1607 ms
TTFT30.0 s1.6 s
Load timeN/A66.4 s
Memory usage21.1 GB22.7 GB
Memory %69%24%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

qwen3.5:35b-a3b-q4_K_M

Speed
28/50
TTFT
14/20
Memory
30/30

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

qwen3.5:35b-a3b-q4_K_M

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View openai/gpt-oss-20b details | View qwen3.5:35b-a3b-q4… 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