Liujgoj-Cantonese-Gemma4-12b-CPT-Unified-i1-GGUF
weighted/imatrix quants of https://huggingface.co/Yvthyvq/Liujgoj-Cantonese-Gemma4-12b-CPT-Unified For a convenient overview and download list, visit our model page for this model....
weighted/imatrix quants of https://huggingface.co/Yvthyvq/Liujgoj-Cantonese-Gemma4-12b-CPT-Unified For a convenient overview and download list, visit our model page for this model....
Agentic tool-calling model for 18 languages, fine-tuned from google/gemma-4-E2B-it and merged to bf16. Accuracy when the model is...
Four GGUF checkpoints for llama.cpp, from 2.91 GB to 8.02 GB. Start with S: 3.76 GB and ≈100%...
name: Second models: — model: Vortex5/G4-Moonlight-Dusk-26B-A4B mergemethod: nearswap chattemplate: auto basemodel: zerofata/G4-MeroMero-26B-A4B parameters: t: 0.0008 dtype: float32 outdtype:...
> This is an independent, unofficial project. It is not affiliated with, endorsed by, or > produced by...
Converted to MLX format from llmfan46/gemma-4-31B-it-qat-q40-unquantized-uncensored-heretic using mlx-lm version 0.31.3**. If you need vision capabilities, use ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-vlm-4Bit. Модальности:Генерация...
This is a second pass at quantizing Gemma 4 31B IT to NVFP4. My earlier upload (gemma-4-31B-it-qat-NVFP4-Blackwell) used...
Türkçe muhakeme yeteneğine sahip, reddetme davranışı kaldırılmış (abliterated) açık kaynak dil modeli. Bu model, AlicanKiraz0/Kizagan-E4B-Turkish-Reasoning-Model üzerinde refusal (reddetme)...
TL;DR: This is not a regular mlxlm convert -q quantization. It is a QAT-lattice-aligned 4-bit conversion of google/gemma-4-26B-A4B-it-qat-q40-unquantized...
A load-and-go FP8 quantization of google/gemma-4-12B-it, plus a reproducible recipe for running it with DeepSeek DSpark speculative decoding...