Tag

Ling-3.0-flash

A 124B hybrid-linear Mixture-of-Experts language model optimized for instruction following, long-context reasoning and agentic workflows, activating ~5.1B parameters per token. Key features include a 256K native context (extendable to 1M), alternating KDA/MLA attention layers, and vLLM/SGLang inference support.

Instella-MoE-16B-A3B-Think

A sparsely activated Mixture-of-Experts (MoE) causal language model with 16B total parameters and 2.8B active parameters per token, released with end-to-end checkpoints and training recipe; trained on AMD Instinct GPUs and licensed for research use.

VibeVoice-ASR-BitNet

Multilingual, real-time ASR for edge CPUs that uses heterogeneous quantization to reduce model size (4.62→1.58 GB) and lower inference latency. Trades some accuracy for 1.6–2.3× faster inference vs. Whisper.cpp and real-time capability on a few CPU threads, making it suitable for memory- and compute-constrained on-device transcription.

Inkling-Small

Generates text from text, image, or audio inputs using a native multimodal, Mixture-of-Experts autoregressive transformer (276B total / 12B active) with up to 1M-token context; targeted at conversational, agentic, coding and multimodal applications.

Kimi K3 (unsloth/Kimi-K3)

Open-weight multimodal Mixture-of-Experts LLM with native vision and a 1,048,576-token context window. 2.8T parameters (104B activated), MXFP4 quantization, released for agentic long-horizon coding, knowledge work, and vision-in-the-loop workflows.

unsloth/Kimi-K3-GGUF

GGUF-quantized build of Moonshot AI's Kimi K3 for local inference: MXFP4-aware quantization, image-text-to-text pipeline support, native vision and a 1,048,576-token context window. Intended for local GGUF runtimes (vLLM, SGLang, TokenSpeed) with Kimi K3 license constraints.

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Real-time streaming multimodal foundation model that uses a codec-native tokenizer (Mage-ViT) to encode motion- and residual-rich regions from video I/P frames, reducing visual token usage by over 75% and enabling up to ~3.5× wall-clock inference speedup after training on ~560M images and 100M video frames.

LFM2.5-Encoder-350M

A 350M-parameter multilingual bidirectional masked-language encoder with an 8,192-token context window, intended for fine-tuning on classification, token-level tasks, retrieval/reranking and semantic-similarity; optimized for long-context CPU inference and on-device use.

LFM2.5-2.6B

A 2.6B causal LLM post-trained for agentic workloads and long-context on-device text generation. Key features: 128K context window and vocabulary, function-calling/tool use support, agentic RL/post-training pipeline, and optimized CPU/Apple inference and multiple deployment formats; suited for agents, RAG and long-context extraction.

NVIDIA NemotronLabs VoiceChat 11B

An end-to-end 11B full-duplex speech model for real-time conversational AI that jointly performs streaming speech understanding and generation, enabling ~450 ms turn-taking, barge‑in and live tool calling in a single unified architecture; research use only.

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Directly maps visual observations and language instructions to continuous robot actions, replacing LLM-centric V→L→A pipelines. Uses separate visual and language encoders with lightweight bidirectional interaction and a compact decoder to cut inference cost and VRAM, achieving ~31 ms latency and <1 GB VRAM on an RTX 4090; suited for real-time robotic manipulation under tight compute budgets.

DeepSeek-V4-Flash-0731-GGUF

Enables local use of a GGUF-quantized DeepSeek-V4-Flash-0731 via Unsloth Dynamic quantizations; provides a Q8 (162GB) lossless option and smaller Q4 variants for lower-memory inference and agentic scenarios using Unsloth tooling.