Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
84 vs 94
Hardware Fit
79 vs 91
Quality Score
86 vs 95

Hardware

qwen/qwen3.6-35b-a3b gpt-oss:20b
MachineASUSFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1632
RAM31 GB64 GB
GPUNVIDIA GeForce RTX 4090, RaphaelAMD Radeon(TM) 8060S Graphics
OScachyos rollingMicrosoft Windows 11 Pro for Workstations 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen/qwen3.6-35b-a3b gpt-oss:20b
Tokens/sec115.848.0
First chunk9 ms357 ms
TTFT310 ms2.3 s
Load timeN/A0.2 s
Memory usage25.3 GB16.4 GB
Memory %83%26%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
9/30

gpt-oss:20b

Speed
50/50
TTFT
11/20
Memory
30/30

Quality

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gpt-oss:20b

Reasoning
19/20
Coding
19/20
Instruction
17/20
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 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