Back to leaderboard

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

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

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Good

Aug 19, 2026 · Intel Core™ Ultra X7 358H

Global Score
72 vs 79
Hardware Fit
35 vs 59
Quality Score
88 vs 88

Hardware

qwen/qwen3.5-35b-a3b GPT-20B:20b
MachineSystem manufacturerGMKtec NucBox EVO-T2S
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ Ultra X7 358H
Cores1616
RAM32 GB64 GB
GPUAMD Radeon RX 9060 XTIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b GPT-20B:20b
Tokens/sec8.319.3
First chunk32 ms2004 ms
TTFT2.0 s10.4 s
Load timeN/A10.4 s
Memory usage28.9 GB12.9 GB
Memory %91%20%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

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

GPT-20B:20b

Speed
26/50
TTFT
3/20
Memory
30/30

Quality

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

GPT-20B:20b

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.5-35b-a3b details | View GPT-20B: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