Home/Models/tturing/Qwen3-Omni-30B-A3B-Thinking-FP8
Qwen3-Omni-30B-A3B-Thinking-FP8
tturing/Qwen3-Omni-30B-A3B-Thinking-FP8
- kind
- fp8
- quant
- fp8 (8-bit)
- family
- qwen
- modality
- any-to-any
- root model
- Qwen/Qwen3-Omni-30B-A3B-Thinking
- provider
- tturing
- license
- other
- language
- en, zh
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 320
- likes
- 1
- created
- —
- last modified
- 2026-05-22T20:19:01+00:00 (2026)
- huggingface
- https://huggingface.co/tturing/Qwen3-Omni-30B-A3B-Thinking-FP8
- tags
- transformerssafetensorsqwen3_omni_moetext-to-audiomultimodalany-to-anyfp8quantizationcompressed-tensorsvllmenzhbase_model:Qwen/Qwen3-Omni-30B-A3B-Thinkingbase_model:quantized:Qwen/Qwen3-Omni-30B-A3B-Thinkinglicense:otherendpoints_compatibleregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.