Back to leaderboard

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

Global Score
92 vs 35
Hardware Fit
95 vs 45
Quality Score
90 vs 30

Hardware

qwen/qwen3-vl-30b qwen3.5:35b-a3b-q4…
MachineASUSMicro-Star International Co., Ltd. MS-7D98
CPUAMD Ryzen 5 5500Intel Core™ i9-14900K
Cores1232
RAM31 GB128 GB
GPUNavi 44 [Radeon RX 9060 XT]Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSNobara Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen/qwen3-vl-30b qwen3.5:35b-a3b-q4…
Tokens/sec24.816.7
First chunk11 ms781 ms
TTFT735 ms30.0 s
Load time11.7 s19.9 s
Memory usage0.6 GB21.8 GB
Memory %2%17%

HW Fit Score Breakdown

qwen/qwen3-vl-30b

Speed
45/50
TTFT
20/20
Memory
30/30

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
0/20
Memory
30/30

Quality

qwen/qwen3-vl-30b

Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:35b-a3b-q4_K_M

Reasoning
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
View qwen/qwen3-vl-30b details | View qwen3.5:35b-a3b-q4… 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