Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
90 vs 78
Hardware Fit
88 vs 51
Quality Score
91 vs 89

Hardware

openai/gpt-oss-20b qwen3.5-35b-a3b-t4…
MachineASUSDell Inc. PowerEdge R820
CPUAMD Ryzen 5 5500Intel Xeon® E5-4650 v2
Cores1280
RAM31 GB256 GB
GPUNavi 44 [Radeon RX 9060 XT]Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSNobara Linux 43Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modeperformancebalanced

Performance

openai/gpt-oss-20b qwen3.5-35b-a3b-t4…
Tokens/sec58.77.1
First chunk6 ms997 ms
TTFT4.5 s997 ms
Load timeN/A45.4 s
Memory usage11.9 GB21.6 GB
Memory %38%8%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
10/20
Memory
28/30

qwen3.5-35b-a3b-t48-c8k…

Speed
6/50
TTFT
15/20
Memory
30/30

Quality

openai/gpt-oss-20b

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

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest