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

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Oct 11, 2026 · AMD Ryzen 5 5500

Global Score
80 vs 74
Hardware Fit
60 vs 100
Quality Score
88 vs 63

Hardware

qwen/qwen3.6-35b-a3b qwen3:0.6b
MachineSystem manufacturerMicrosoft WSL
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 5 5500
Cores1612
RAM31 GB8 GB
GPUNavi 44 [Radeon RX 9060 XT]Integrated / Unknown
OSUbuntu 26.04.1 LTSUbuntu 26.04.1 LTS
Archx64x64
Power Modeperformanceunknown

Performance

qwen/qwen3.6-35b-a3b qwen3:0.6b
Tokens/sec15.0257.7
First chunk49 ms92 ms
TTFT759 ms675 ms
Load timeN/A4.7 s
Memory usage22.2 GB0.9 GB
Memory %71%11%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

qwen3:0.6b

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

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

qwen3:0.6b

Reasoning
13/20
Coding
6/20
Instruction
12/20
Structured
13/15
Math
12/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
View qwen/qwen3.6-35b-a3b details | View qwen3:0.6b 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