Score 3Qwen3VLF16vision

Qwen3VL-2B-Thinking-F16

Qwen3VL-2B-Thinking-F16 is available from the local Hugston.com model catalog.

Deployment profile

3.21 GBFile size

4.3 GBSuggested VRAM

0Downloads

0Votes

Community5%

Downloads5%

Novelty3%

VRAM Fit93%

93%

mmproj-GLM-OCR-MTP-Q8_0mmproj · Q8_0

mmproj-AbirayOvisOCR2-GGUF-BF16mmproj · BF16

ruvltra-claude-code-0.5b-q4_k_mruvltra · Q4_K_M

Reasoning-Medical-27B.Q4_K_MReasoning · Q4_K_M

Tested-OmniCoder-9B-Claude-Opus-High-Reasoning-Distill.Q8_0Tested · Q8_0

NuMarkdown-8B-Thinking.Q8_0NuMarkdown · Q8_0

NuMarkdown-8B-Thinking.mmproj-f16NuMarkdown · F16

Hugston-kai-os-Qwen3.6-27b-Opus4.6-reasoning.Q4_K_MHugston · Q4_K_M