qwen3-vl:30b
OLLAMA GGUFqwen3vlmoe · 31.1B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
huihui-devstral-small-2-24b-instruct-2512-abliterated-i1
LM-STUDIO GGUFmistral3 · 24B · Q4_K_S
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
80 vs 78
Hardware Fit
98 vs 74
Quality Score
72 vs 79
Hardware
qwen3-vl:30b huihui-devstral-sm…
MachineASUSSystem manufacturer
CPUIntel Core™ Ultra 9 285KAMD Ryzen 7 5800X 8-Core Processor
Cores2416
RAM47 GB32 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsAMD Radeon RX 9060 XT
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3-vl:30b huihui-devstral-sm…
Tokens/sec208.917.5
First chunk102 ms20 ms
TTFT684 ms279 ms
Load time0.1 sN/A
Memory usage22.0 GB15.6 GB
Memory %47%49%
HW Fit Score Breakdown
qwen3-vl:30b
Speed
50/50
TTFT
20/20
Memory
28/30
huihui-devstral-small-2…
Speed
29/50
TTFT
20/20
Memory
25/30
Quality
qwen3-vl:30b
Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
huihui-devstral-small-2…
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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