qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
92 vs 66
Hardware Fit
95 vs 99
Quality Score
90 vs 52
Hardware
qwen/qwen3-vl-30b granite3.1-moe:3b
MachineASUSDell Inc. Inspiron 15 3530
CPUAMD Ryzen 5 5500Intel Gen Intel® Core™ i7-1355U
Cores1212
RAM31 GB31 GB
GPUNavi 44 [Radeon RX 9060 XT]Raptor Lake-P [Iris Xe Graphics]
OSNobara Linux 43cachyos rolling
Archx64x64
Power Modeperformancelow-power
Performance
qwen/qwen3-vl-30b granite3.1-moe:3b
Tokens/sec24.827.2
First chunk11 ms527 ms
TTFT735 ms527 ms
Load time11.7 s1.9 s
Memory usage0.6 GB2.9 GB
Memory %2%9%
HW Fit Score Breakdown
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
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
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
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