Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Not Rec.

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

Global Score
80 vs 84
Hardware Fit
60 vs 65
Quality Score
88 vs 92

Hardware

qwen/qwen3.6-35b-a3b openai/gpt-oss-20b
MachineSystem manufacturerASUS
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 7 7800X3D 8-Core Processor
Cores1616
RAM31 GB31 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 4090, Raphael
OSUbuntu 26.04.1 LTScachyos rolling
Archx64x64
Power Modeperformanceperformance

Performance

qwen/qwen3.6-35b-a3b openai/gpt-oss-20b
Tokens/sec15.0221.5
First chunk49 ms5 ms
TTFT759 ms30.0 s
Load timeN/AN/A
Memory usage22.2 GB21.1 GB
Memory %71%69%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
25/50
TTFT
20/20
Memory
15/30

openai/gpt-oss-20b

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

Quality

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
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

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
View qwen/qwen3.6-35b-a3b details | View openai/gpt-oss-20b 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