Qwen3-VL-30B-A3B-Instruct-FP8
unsloth/Qwen3-VL-30B-A3B-Instruct-FP8
- kind
- fp8
- quant
- fp8 (8-bit)
- family
- qwen
- modality
- image-text-to-text
- root model
- Qwen/Qwen3-VL-30B-A3B-Instruct-FP8
- provider
- unsloth
- license
- apache-2.0
- language
- —
- context
- ,
- library
- —
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 382
- likes
- 1
- created
- —
- last modified
- 2025-11-24T10:43:59+00:00 (2025)
- huggingface
- https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Instruct-FP8
- tags
- safetensorsqwen3_vl_moeunslothimage-text-to-textconversationalarxiv:2505.09388arxiv:2502.13923arxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen3-VL-30B-A3B-Instruct-FP8base_model:quantized:Qwen/Qwen3-VL-30B-A3B-Instruct-FP8license:apache-2.0fp8region:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.