Back to leaderboard

qwen3-vl:30b

OLLAMA GGUF

qwen3vlmoe · 31.1B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
80 vs 88
Hardware Fit
98 vs 85
Quality Score
72 vs 89

Hardware

qwen3-vl:30b huihui-qwen3.6-35b…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ Ultra 9 285KAMD Ryzen 5 5600X 6-Core Processor
Cores2412
RAM47 GB47 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

qwen3-vl:30b huihui-qwen3.6-35b…
Tokens/sec208.937.7
First chunk102 ms18 ms
TTFT684 ms2.9 s
Load time0.1 sN/A
Memory usage22.0 GB26.1 GB
Memory %47%56%

HW Fit Score Breakdown

qwen3-vl:30b

Speed
50/50
TTFT
20/20
Memory
28/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

qwen3-vl:30b

Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
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