unsloth releases DeepSeek-V4.1-Flash GGUF quantized builds under MIT license
unsloth · hf · 2026-10-18
unsloth published GGUF quantized builds of DeepSeek-V4.1-Flash-1017 on Hugging Face, enabling local deployment of the model. It runs an image-text-to-text pipeline, is MIT-licensed, and is compatible with transformers and endpoints.
Related event: Unsloth quietly posts DeepSeek-V4.1-Flash GGUF quantization on Hugging Face(2 posts)→
More from Models
- OpenAI critique: users miss cancelled GPT-6.1 Astra as $500 tier flops — koltregaskes · 2026-10-19
- Rauch teases 'Pi-maxing' week, Malte Ubl asks to estimate tokens to compute pi — cramforce · 2026-10-19
- deepfates jokes agents' auto mode got overcautious because of jailbreak abuse — rickasaurus · 2026-10-19
- Rumor: Google working on Gemini Omni 1.5 with 15-second video input — lyraxana · 2026-10-19
- Qwen3.8 27B benchmarks on NVIDIA RTX Spark: 19.3 tok/s decode, 100% accuracy — draginol · 2026-10-19
- Allie Miller: Claude leads on models, Codex on features — she uses both — alliekmiller · 2026-10-19