Grug-12B-GGUF
mradermacher/Grug-12B-GGUF
- kind
- gguf
- quant
- gguf (4-bit)
- family
- misc
- modality
- —
- root model
- kai-os/Grug-12B
- provider
- mradermacher
- license
- other
- language
- en
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 1,704
- likes
- 2
- created
- —
- last modified
- 2026-07-02T16:22:43+00:00 (2026)
- huggingface
- https://huggingface.co/mradermacher/Grug-12B-GGUF
- tags
- transformersggufsafetensorsfine-tunedqlorareasoningcompact-reasoninggemma-4endataset:hotdogs/uka-glm-5.2dataset:Scale-or-Reason/general-reasoning-ift-pairsdataset:samcheng0/lumia-reasoning-sft-v1dataset:HSH-Intelligence/verified-math-reasoning-3kdataset:kd13/CodeDebug-Instruct-v2-Reasoningdataset:Madarabr/cortex-adaptive-thinkingdataset:CL-From-Nothing/code_rose_initial_1_7B_SFT_10K_rollouts_Qwen3-4B-Thinking-2507_k12_t0.7_maxtok12288base_model:kai-os/Grug-12Bbase_model:quantized:kai-os/Grug-12Blicense:otherendpoints_compatibleregion:usconversational
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.