Back to leaderboard

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

qwen2-57b:57B

OLLAMA GGUF

qwen2moe · 57.4B · Q4_K_M

Good

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
92 vs 67
Hardware Fit
95 vs 51
Quality Score
90 vs 74

Hardware

qwen/qwen3-vl-30b qwen2-57b:57B
MachineASUSGMKtec NucBox EVO-T2S
CPUAMD Ryzen 5 5500Intel Core™ Ultra X7 358H
Cores1216
RAM31 GB64 GB
GPUNavi 44 [Radeon RX 9060 XT]Intel(R) Arc(TM) B390 GPU
OSNobara Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen/qwen3-vl-30b qwen2-57b:57B
Tokens/sec24.88.6
First chunk11 ms1573 ms
TTFT735 ms1.6 s
Load time11.7 s29.0 s
Memory usage0.6 GB32.8 GB
Memory %2%52%

HW Fit Score Breakdown

qwen/qwen3-vl-30b

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

qwen2-57b:57B

Speed
10/50
TTFT
17/20
Memory
24/30

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

qwen2-57b:57B

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3-vl-30b details | View qwen2-57b:57B 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