AI Model2026
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.
AI Model2026
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.
AI Model2026
GGUF-quantized build of Qwen3.8-Flash-Next for image-text-to-text inference and local deployment. Ships with Unsloth Dynamic 3.0 quantization, thinking-mode controls (preserve_thinking, reasoning_effort), and native long-context support (262k, extensible to 1M with YaRN).
AI Model2026
Provides per-tensor non-uniform GGUF quantizations of Qwen3.8-27B using GSQ and RCO, delivering high accuracy at 2.5–3.5 bits and including a BF16 vision projector for multimodal use. Optimized to run unmodified in llama.cpp, Ollama, and LM Studio.
AI Model2026
Sparse MoE causal LLM that uses Mixture-of-Value Attention (MoVA) to store 36B parameters while activating ~4B per token; supports a native 524,288-token context and is released with final checkpoints, training data, and training code under open license.
AI Model2026
A TURBO multi-stage fine-tune of Qwen3.8‑27B that shortens internal “thinking” token blocks and raises ARC benchmarks (8‑bit ARC‑C ≈735, ARC‑E ≈882). It ships GGUF quants (regular and MTP, Neo‑Imatrix), vision support and 256k context for local multimodal inference on consumer GPUs.
Converts a natural-language function specification into a reusable local neural function by using teacher models to synthesize examples and finetuning a small adapter for a compact interpreter. Achieves higher semantic accuracy (83.6% on FuzzyBench-Hard) at the cost of roughly one minute compile time; produces versionable PAW artifacts for local deployment.
Shows that fully quantizing all 496 linear layers—including the recurrent Gated DeltaNet—of a hybrid 27B LLM to 4-bit NVFP4 W4A4 preserves benchmark accuracy while reducing model size to 17.5 GiB and improving prefill speed; includes a calibrated NVFP4 checkpoint.
Compresses KV cache for long-chain reasoning by keeping prompt tokens and evicting remaining entries uniformly at random per attention head; across four models and six reasoning tasks it matches the strongest prior evictor while delivering 32–43% higher vLLM throughput. Relies on prompt protection and redundancy across heads/text to retain reasoning traces; suitable when static memory budgets and higher serving throughput are priorities.
AI Model2026
Runs a 35B-class sparse MoE LLM with SSD-streamed experts, 4-bit quantization, prerouter routing prediction and Recover-LoRA adapters to enable ~2.9–3 GiB active memory and interactive decoding (~15 tok/s) for on-device inference.
AI Model2026
Multimodal agentic model for long-horizon computer and browser tasks, with visual self-correction and function-calling. The Pro variant is a 397B Mixture-of-Experts (≈17B active) model with a 262,144-token context window, Docker deployment recipes, and weights currently marked “coming soon.”
AI Model2026
Open-weights preview checkpoint for a multimodal reasoning model that generates text from text and image/video inputs, exposes adjustable reasoning effort and tool-calling, and supports an extended 262,144-token context for long-horizon tasks and agent-style workflows.