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

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
80 vs 88
Hardware Fit
60 vs 91
Quality Score
88 vs 87

Hardware

qwen/qwen3.6-35b-a3b Qwen3-30B:30b
MachineSystem manufacturerHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1632
RAM31 GB31 GB
GPUNavi 44 [Radeon RX 9060 XT]AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen/qwen3.6-35b-a3b Qwen3-30B:30b
Tokens/sec15.041.8
First chunk49 ms453 ms
TTFT759 ms453 ms
Load timeN/A19.5 s
Memory usage22.2 GB17.9 GB
Memory %71%58%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

Qwen3-30B:30b

Speed
50/50
TTFT
20/20
Memory
21/30

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

Qwen3-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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