Tag
Explore by tags
Mixture-of-Experts LLM tuned for mathematical and coding reasoning, with ~760M active / 8.4B total parameters and post-training for improved stepwise reasoning. Optimized for inference efficiency (vLLM/transformers forks) so it can run in computation-constrained or local deployments; Apache-2.0 licensed.
Merges Unsloth UD XL quantized GGUF of Qwen3.6-27B with compact Q8_0 MTP heads to enable multi-token (speculative) decoding on llama.cpp builds that support MTP; aimed at image-text-to-text usage with reduced MTP overhead.
Processes text and images to produce conversational, reasoning-focused multilingual outputs for agentic workflows. Built as a sparse MoE decoder (25B active / 218B total parameters) with 128K context and available in BF16/FP8/W4A4 quantizations to balance quality and deployability.
A 30B mixture-of-experts multilingual translation model supporting 33 languages and instruction-following translation. Offers MoE architecture, fast-thinking mode, and quantized/deployment-ready variants for production translation and subtitle tasks.
A family of multilingual translation models optimized for real-world, instruction-following translation across 33 languages. The 1.8B model targets on-device use with extreme quantization (≈440 MB via AngelSlim), while 7B/30B variants trade size for higher accuracy.
7B multilingual translation model optimized for instruction-following and low-latency deployment across 33 languages; provides quantized/FP8/GGUF builds and integrations (vLLM, llama.cpp) for server and on-device inference.
Provides a quantized GGUF build of Qwen3.6‑27B with MTP (multi‑token prediction) support for faster local inference. Packaged for GGUF-compatible runners (llama.cpp) and Hugging Face/transformers workflows, with deployment notes for CPU/GPU and vLLM/SGLang integration.
A GGUF-quantized build of Qwen3.6-35B packaged by unsloth for local and accelerated inference. Adds MTP speculative decoding guidance and deployment notes for llama.cpp, vLLM, SGLang and long-context/multimodal use cases.
W4A4-quantized build of a 25B-parameter multimodal LLM that produces text from image+text inputs and supports conversational tool use. Trades very small quality differences for much lower GPU memory and latency so inference can run on smaller accelerators (vLLM support).
Provides a locally runnable 26.9B Qwen3.6 checkpoint that surgically reduces refusal behavior in weight space while preserving capability; ships bfloat16 safetensors and a GGUF quant ladder for local runtimes and red-team evaluation.
Converts long-form multi-speaker audio/video into a compact, speaker-aware transcript with timestamps and anonymous speaker labels in one pass. Combines ASR and diarization in a single model, supports custom prompts/hotwords, and targets meetings, podcasts, interviews and long recordings.
Generates temporally coherent MP4 videos from a single input image plus text instructions, with configurable resolution, frame count, and optional AAC audio. Optimized for NVIDIA GPU stacks and integrates with vLLM‑Omni and Hugging Face Diffusers for production inference and research workflows.