Tag

Qwen3.6-35B-A3B-Escha-W2

Provides a 2‑bit quantized build of Qwen3.6‑35B‑A3B for local serving via an OpenAI‑compatible HTTP API. Key features: 12.3 GB on disk, eschamoe mixed 2/3‑bit expert quantization with int8 dense layers, runs on a single 16–24 GB NVIDIA GPU and ships with Escha SGLang and ZML runtimes.

XYZ-Aquila-pro

An open-weight LLM checkpoint post-trained for agentic deep search: Qwen-compatible reasoning and tool-call formats optimized for web browsing, multi-source evidence aggregation, long-horizon planning and recovery from failed interactions; typically paired with the AxisAgentic harness.

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.

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Provides a portable, robot-free UMI capture pipeline and shows that policies post-trained only on this high-fidelity data deploy directly on real robots matching teleoperation baselines. Capture achieves ~3 mm end-effector accuracy, microsecond sync, ultra-wide FOV, and releases 2,000h HiFi-UMI-2K.

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.

LFM2.5-2.6B-GGUF

Provides a GGUF-quantized, llama.cpp-compatible build of LiquidAI's LFM2.5-2.6B for local CPU inference and offline deployment. Supports multilingual generation and long-context workflows; optimized for low-memory, on-device use.

BigBang-V1

Finetunes Qwen3.6‑35B using an adversarial generator–critic loop that synthesizes ~10,000 verifiable “frontier” tasks to boost scientific research, long‑horizon reasoning, coding and tool use; supports an extended 262,144‑token context and common serving stacks.

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Frames LLM routing as a sequential decision process and introduces LLMRouter plus the xRouteBench benchmark to develop, evaluate, and deploy learned routing policies across heterogeneous LLMs, optimizing response quality versus inference cost.

Muse Glimmer-30B

A 29.6B-parameter multimodal causal language model with a dedicated ViT-G/14 perception encoder for running agentic, tool-using, multimodal reasoning locally on consumer hardware. Offers 4-bit quantized weights and a DFlash drafter for speculative decoding to reduce memory and speed up generation.

Muse Glimmer-30B-GGUF

A GGUF release of Meta's Muse Glimmer 30B optimized for local multimodal agent inference; includes two quantized text builds, a perception encoder for image input, and an optional DFlash drafter for speculative decoding—fits on 24–32 GB VRAM.

Muse Glimmer-30B-GGUF

Runs a quantized, locally executable 29.6B multimodal causal language model optimized for agentic workflows. Includes a perception encoder for image+text input, 4-bit quantized weights for 24–32GB devices, a DFlash drafter for speculative decoding, and robust tool-call support.

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.