Home/Models/mradermacher/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-i1-GGUF
gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-i1-GGUF
mradermacher/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-i1-GGUF
- kind
- gguf
- quant
- gguf (1-bit)
- family
- gpt-oss
- modality
- text-generation
- root model
- AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts
- provider
- mradermacher
- license
- apache-2.0
- language
- en
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 1,059
- likes
- 2
- created
- —
- last modified
- 2025-12-04T21:03:26+00:00 (2025)
- huggingface
- https://huggingface.co/mradermacher/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-i1-GGUF
- tags
- transformersggufmixture-of-expertsmoeexpert-pruninggpt-ossopenaireasoningallspecializedefficienttransformercausal-lmtext-generationpytorchpruned-modeldomain-specificendataset:AmanPriyanshu/GPT-OSS-20B-MoE-expert-activationsbase_model:AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-expertsbase_model:quantized:AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-expertslicense:apache-2.0endpoints_compatibleregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.