Home/Models/mradermacher/Ornith-1.0-35B-FP8-BLOCK-MTP-i1-GGUF
Ornith-1.0-35B-FP8-BLOCK-MTP-i1-GGUF
mradermacher/Ornith-1.0-35B-FP8-BLOCK-MTP-i1-GGUF
- kind
- gguf
- quant
- gguf (8-bit)
- family
- misc
- modality
- —
- root model
- shisa-ai/Ornith-1.0-35B-FP8-BLOCK-MTP
- provider
- mradermacher
- license
- mit
- language
- en
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 5,803
- likes
- 5
- created
- —
- last modified
- 2026-07-04T05:54:33+00:00 (2026)
- huggingface
- https://huggingface.co/mradermacher/Ornith-1.0-35B-FP8-BLOCK-MTP-i1-GGUF
- tags
- transformersgguffp8fp8-blockcompressed-tensorsllm-compressorqwen3.5qwen3.6moemtpspeculative-decodingvllmcodereasoningenbase_model:shisa-ai/Ornith-1.0-35B-FP8-BLOCK-MTPbase_model:quantized:shisa-ai/Ornith-1.0-35B-FP8-BLOCK-MTPlicense:mitendpoints_compatibleregion:usimatrixconversational
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.