전체 검색
AI 모델 84767
- Nemotron-3.5-Bolt-74B-A9B-MLX-mixed46↗
hermitdave
- Homura-30B-GGUF↗
hyrelabs
**HYRE's first in-house model** — an agent-tuned, uncensored derivative of Meta's Muse Glimmer 30B, built for autonomous agents that need tool-calling and a straight-talking voice with no refusal walls. HOMURA is **not** a from-scratch model. It is a LoRA fine-tune applied on top of a community-decensored Muse Glimmer, then merged and quantized. The derivation chain is honest and traceable: 1. **Meta — Muse Glimmer 30B** (Apache 2.0): the agent-native base (tool use, long-horizon planning, failure recovery). 2. **darkc0de — Muse-Glimmer-30B-heretic**: refusal behavior removed (abliteration), while tool-calling, reasoning, and the vision encoder were preserved. 3. **HYRE — HOMURA**: our contribution — a LoRA (r=16) tuned on a HYRE agent + uncensored-persona dataset, applied to the **language tower only** (the vision tower is untouched), then merged at f16 and quantized to GGUF.
- granite-3.3-8b-base-GGUF↗
ibm-granite
- llama-7b-wanda-70pct↗
ikimyaii
- BgGPT-Gemma-3-27B-IT↗
INSAIT-Institute
BgGPT 3.0 is a series of Bulgarian-adapted LLMs based on Gemma 3, developed by INSAIT. Available in 4B, 12B and 27B sizes. 1. **Vision-language understanding** — The models understand both text and images within the same context. 2. **Instruction-following** — Trained on a broader range of tasks, multi-turn conversations, complex instructions, and system prompts. 3. **Longer context** — Effective context of 131k tokens for longer conversations and complex instructions. 4. **Updated knowledge cut-off** — Pretraining data up to May 2025, instruction fine-tuning up to October 2025. Load the model in FP8 at runtime for ~2x memory reduction with minimal quality loss — no separate quantized checkpoint needed:
- MiniMax-H3-curve-GGUF↗
joeygambino
GGUF quantizations of MiniMax-H3's 33B video+audio DiTs, built from MiniMax's **pruned** checkpoints. Same model, same quant tiers as the original-form repo, **about 40% smaller** - and a Q8_0 that fits a 24 GB card. `fl2va` = text/first-last-frame to video+audio (T2V and I2V). `ref2va` = reference-conditioned generation (identity from up to 9 images, 3 videos with soundtracks, 3 voice clips). Runs in ComfyUI with ComfyUI-GGUF plus a one-line architecture patch (node pack: **ComfyUI-H3-Multishot**; workflows: **MiniMax-H3-Multishot-Workflow**).
- Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix↗
Lewdiculous
- Lythri-4B-A2B↗
Lythri
- LCO-Embedding-Omni-3B-GGUF↗
marksverdhei
- xclip-base-patch32-16-frames↗
Microsoft
X-CLIP model (base-sized, patch resolution of 32) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
