Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
94 vs 72
Hardware Fit
91 vs 35
Quality Score
95 vs 88

Hardware

gpt-oss:20b qwen/qwen3.5-35b-a3b
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)System manufacturer
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 5800X 8-Core Processor
Cores3216
RAM64 GB32 GB
GPUAMD Radeon(TM) 8060S GraphicsAMD Radeon RX 9060 XT
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

gpt-oss:20b qwen/qwen3.5-35b-a3b
Tokens/sec48.08.3
First chunk357 ms32 ms
TTFT2.3 s2.0 s
Load time0.2 sN/A
Memory usage16.4 GB28.9 GB
Memory %26%91%

HW Fit Score Breakdown

gpt-oss:20b

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

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

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

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
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 qwen/qwen3.5-35b-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