Back to leaderboard

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

qwen3.8-27b-claude-opus-reasoning-distilled

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Aug 20, 2026 · Apple M4 Max

Global Score
92 vs 80
Hardware Fit
95 vs 63
Quality Score
90 vs 87

Hardware

qwen/qwen3-vl-30b qwen3.8-27b-claude…
MachineASUSMacBook Pro
CPUAMD Ryzen 5 5500Apple M4 Max
Cores1216
RAM31 GB128 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4 Max
OSNobara Linux 43macOS 26.5.2
Archx64arm64
Power Modeperformancebalanced

Performance

qwen/qwen3-vl-30b qwen3.8-27b-claude…
Tokens/sec24.824.0
First chunk11 ms20 ms
TTFT735 ms4.5 s
Load time11.7 sN/A
Memory usage0.6 GB15.7 GB
Memory %2%12%

HW Fit Score Breakdown

qwen/qwen3-vl-30b

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

qwen3.8-27b-claude-opus…

Speed
27/50
TTFT
6/20
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

qwen3.8-27b-claude-opus…

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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