Tag

Qwen Sharp Chat Templates

Provides a drop-in Jinja chat template for Qwen 3.5/3.6/3.8 that reduces reasoning-token waste, enforces a concise terseness system prompt, and preserves in-chat reasoning and tool-call rendering across turns. Terseness is on by default but switchable per request; no model weights are changed.

Ling-3.0-tiny

Lightweight sparse-MoE LLM (7.9B params, ~1.3B activated per token) designed for hybrid multi-step reasoning and agentic tasks. Uses a KDA–MLA hybrid attention stack and a 128-expert sparse FFN; offered in BF16/FP8/INT4 for local and edge deployment.

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

A customizable 30B-parameter Mixture-of-Experts LLM (3B active) in BF16 for low-latency, high-throughput agent workflows; supports speculative decoding (MTP/DSpark/DFlash) and up to 1M-token contexts. Released with open weights and recipes under OpenMDW-1.1, intended for post-training, domain adaptation, and research on NVIDIA GPU stacks.

LFM2.5-VL-3B

Multimodal vision-language model optimized for on-device image+text tasks: image captioning, full-page OCR with layout annotation, grounding/bounding-box prediction, and function calling. Built on the LFM2.5-2.6B backbone with a SigLIP2 NaFlex 400M vision encoder and tuned for low-latency, low-memory edge inference.

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

Open-weight 30B-parameter Mixture-of-Experts LLM with 3B active params, NVFP4-quantized checkpoint, and speculative-decoding support for long-context (up to 1M tokens) agentic, chat, reasoning and tool-calling workloads optimized for NVIDIA GPUs.

Qwen3.8-27B-FP8

Provides an FP8-post-trained 27B multimodal causal language model with a native vision encoder, large-context support (262,144 native, extensible to 1,000,000), controllable thinking-mode reasoning, and compatibility with common inference engines for deployment.

DeepSeek-V4-Pro-0813

Provides a Mixture-of-Experts language model tuned for million-token contexts and agentic workflows, with DSpark speculative decoding, FP4/FP8 mixed-precision support, and vLLM/SGLang deployment recipes for low-latency production inference.

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

Separates knowledge storage (a global Memory) from iterative reasoning operators (multiple Reasoners) to improve knowledge compression and inference efficiency; reports a 7B model matching baseline with 62.6% of training data and a 35B Intern-S2-Mobius achieving ~4x end-to-end speedup.

Qwen3.8-9B Distill

A 9B-parameter distillation that transfers chain-of-thought reasoning from Qwen3.8 into the Qwen3.5-9B architecture for single‑GPU deployment; trained on ~70,000 teacher traces, it offers 262k-token context, native function-calling, and improved MMLU performance.

Qwen3.8-27B-Uncensored-FP8

An FP8-quantized, uncensored mirror of Qwen3.8-27B for image-text-to-text tasks — preserves native multimodal vision and very long context while targeting transformers/vLLM deployments; intended for offline testing and red-teaming and may bypass built-in safety filters.

Qwen3.8-27B-Uncensored-GGUF

Local GGUF build of Qwen 3.8 27B with the refusal direction ablated for llama.cpp; includes vision projector (mmproj), MTP speculative head, a 262k context window and multiple quant tiers (Q2–Q8, F16). Research-only release that requires updated llama.cpp and explicit safety layers.

Ornith-1.5-9B

A 9B open-weight reasoning LLM that uses a self-improvement loop to auto-generate tasks, construct scaffolds, and optimize rollouts for stronger agentic coding and long-context reasoning. Single-GPU deployable, supports tool-calling and a 262,144-token context window.