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.
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.
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.
Provides an abliterated (refusal-removed) build of Qwen3.8-27B for offline research and red‑teaming, keeping multimodal vision, an MTP speculative head, and a 262,144-token context. It has no built-in safety guardrails and is released under Apache‑2.0 for research use only.
A 35B mixture-of-experts LLM tuned for agentic coding and end-to-end self-improvement: it jointly generates tasks, scaffolds, and solution rollouts. Activates ~3B params/token, supports 256K context (extendable), and emits chain-of-thought plus OpenAI-style tool calls.
GGUF build of Ornith-1.5's 35B mixture-of-experts model (A3B) for local inference — activates ~3B params per token, supports up to 262,144 tokens, emits separate reasoning traces and OpenAI-style tool calls, optimized for agentic coding and long-context use cases.
A draft model that predicts whole blocks of tokens in parallel for speculative decoding of Qwen3.8-27B. Uses block-diffusion drafting with per-position candidate sets and a selector plus dynamic convolutions to keep end-of-block accuracy, increasing accepted tokens per verification and end-to-end throughput versus autoregressive decoding.
A 9B dense reasoning LLM optimized for single‑GPU deployment and terminal-based coding agents, with long-context support (up to 262,144 tokens) and GGUF/quantized builds for edge/mobile. Strong on coding and agentic benchmarks.
A 4B-parameter on-device general-purpose LLM for chat, writing, translation, coding and agentic workflows with native 1,000,000-token context. Uses a hybrid attention design to enable long-context efficiency, pretrained on ~20T tokens, and compatible with vLLM, llama.cpp, Ollama and LM Studio.
Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.
Provides FP8-quantized Hugging Face weights and config for Qwen3.8-Flash-Next (block size 128), preserving near-original performance. Compatible with Transformers, vLLM, SGLang and TokenSpeed; intended for efficient deployment of a 125B multimodal causal LM with very long context support.
Experimental open-weight multimodal LLM preview designed for long-context, agentic workloads. It introduces hybrid sparse attention (QSA), gated residual streams, and large offloadable n‑gram embeddings (51B) alongside a high-sparsity MoE (125B total, 6B active) to trade memory for runtime efficiency and improved long-horizon reasoning.