Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
94 vs 79
Hardware Fit
91 vs 59
Quality Score
95 vs 87

Hardware

gpt-oss:20b qwen3.6-35b-a3b
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)Docker Container
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i9-11900H
Cores3216
RAM64 GB15 GB
GPUAMD Radeon(TM) 8060S GraphicsTigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

gpt-oss:20b qwen3.6-35b-a3b
Tokens/sec48.09.3
First chunk357 ms21 ms
TTFT2.3 s3.6 s
Load time0.2 s32.0 s
Memory usage16.4 GB1.8 GB
Memory %26%12%

HW Fit Score Breakdown

gpt-oss:20b

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

qwen3.6-35b-a3b

Speed
17/50
TTFT
12/20
Memory
30/30

Quality

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

qwen3.6-35b-a3b

Reasoning
17/20
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
View gpt-oss:20b details | View qwen3.6-35b-a3b 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