qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
92 vs 76
Hardware Fit
95 vs 91
Quality Score
90 vs 69
Hardware
qwen/qwen3-vl-30b codestral:latest
MachineASUSGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD Ryzen 5 5500Intel Core™ i5-14400F
Cores1216
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 5060 Ti
OSNobara Linux 43Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
qwen/qwen3-vl-30b codestral:latest
Tokens/sec24.827.4
First chunk11 ms86 ms
TTFT735 ms86 ms
Load time11.7 s7.2 s
Memory usage0.6 GB12.6 GB
Memory %2%40%
HW Fit Score Breakdown
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
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
codestral:latest
Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest