#Open source/Repo

AIUnsloth's Qwen3.8-27B GGUF has become the most-liked GGUF model of all time on Hugging Face, reaching 10 million downloads and 3.7K likes in 24 days. The post links the GGUF model page and a Qwen3.8 guide on the Unsloth docs site.

AIHugging Face's Leandro von Werra asked Astra to build an interactive star map for his old telescope, and Astra also built a full simulator while a missing cable delays connecting the telescope to the dashboard. The simulator is available as a Hugging Face Space at The post does not specify what Astra is.

AIOpenBMB released JustRL-II-base-model, the pre-RL starting checkpoint for the JustRL II math-reasoning case study, scoring about 61% on AIME 2025 before reinforcement learning. The full JustRL II recipe reaches 81% on AIME 2025 in about 300 RL steps from this checkpoint, versus about 74% for a standard GRPO baseline. The Llama-architecture weights are available on Hugging Face and are intended for reproducing the recipe and research on long-CoT RL, not general assistant use.

AIOpenBMB released MiniCPM5-2B-DSpark, a 323,776,001-parameter DSpark draft checkpoint with five layers that proposes seven draft tokens per forward pass for the MiniCPM5-2B target model. The model, trained on 7,054,154,509 tokens with an average acceptance length of 5.5174 at T=0 and 4.0514 at T=1.0, is served through SGLang with DSPARK speculative decoding. It is released in BF16 under the Apache-2.0 License.

AITencent has open-sourced EVIE-8B, an 8.4B-parameter visual document retriever that scores 66.75 nDCG@10 on ViDoRe V3 and ranks first on that leaderboard's mean task score of 66.24. The model uses 4096D per-token multi-vector embeddings with MaxSim late-interaction scoring and bidirectional attention, and it serves as the teacher for the lightweight EVIE-4.5B model. Model weights, inference pipelines, and evaluation suites are available, while the formal research paper is promised for a future release.

AITencent released EVIE-4.5B, a 4.5B-parameter visual document retrieval model, with weights, training pipelines, HAC token compression, and evaluation suites open-sourced on Hugging Face. It scores 66.02 on ViDoRe V3 and ranks second on that leaderboard behind the 8.4B EVIE-8B, which scores 66.24. Its Prefix-MRL head lets a single 2048D projection be truncated to 64–2048 dimensions at runtime without separate models.

AIHermes now includes a local backend that runs Unsloth UD-Q4_K_XL and UD-Q4_K_M quants for DeepSeek-V4-Flash, Qwen3.8-27B, Qwen3.6-35B-A3B, and Qwen3.8-Flash-Next. The post says these models can be run locally in one click, with Unsloth GGUFs supported.

AIUnsloth GGUF models, including Qwen3.8-27B, Qwen3.8-Flash, and DeepSeek-V4-Flash, can now be run locally in one click through Hermes. Hermes Desktop automatically reads hardware, selects a suitable model, downloads it, and configures the runtime.

AILM Studio has released Bionic, linked from its website at which the post says lets users continue their work. The post provides no further details about its features, models, or pricing.

AIAli Ghodsi congratulated Clement Delangue and Jensen Huang and said the deal will be good for the industry and open source. The author's own post is short, and the quoted NVIDIA message says NVIDIA is acquiring Hugging Face and will be its new home.

AIBAAI and Hao Tang's team at Peking University's School of Computer Science released GaussianMind, an audio-language model built on RoboBrain and OpenMOSS Audio. The model is available on Hugging Face and loads through custom Transformers code with trust_remote_code=True.

AICohere Labs released Tiny Aya L2-Thinker, an open-weights 3.35 billion parameter multilingual reasoning model that thinks in the same language as the user's prompt before answering. The model supports in-language reasoning for 44 languages plus English, with coverage extended to 20+ more languages through additional non-reasoning instruction data, and has a 32K context length. It is licensed under CC-BY-NC and is available on Hugging Face.

AIAi2 has published supplemental checkpoints for its ACE2S-SHiELD+ climate model on Hugging Face, covering four ablation configurations that test random CO2 data and energy conservation. Each configuration includes two random-seed models, and the repository recommends the main ACE2S-SHiELD+ checkpoint for most uses. The checkpoints are licensed under Apache 2.0 for research and educational use.

AIGoogle has released GNM v3.0, a parametric 3D statistical model of the human head, with weights published on Hugging Face and Kaggle under the Apache 2.0 license. The model gives controllable identity, expression, head pose, and internal anatomy including eyeballs, teeth, and tongue, and supports NumPy, JAX, PyTorch, and TensorFlow backends.

AITencent Hunyuan says its Hy4 preview model found inference bottlenecks on its own and raised end-to-end throughput by 31.8% through operator fusion and communication optimizations. The post says the gain holds across context lengths and concurrency levels. The release is listed at 770B total parameters with 49B active and a 1M context window, with links to the Hy blog, Hugging Face, and GitHub.

AIThe Llama app for Mac now includes a simple request builder for llama.cpp's REST API. The feature lets users construct requests to the llama.cpp server directly within the app.

AIShanghai AI Lab's InternLM has published Intern Lumina U2, a 16B-parameter MoE model with 1B active parameters that handles text QA, image generation and editing, and image, video, and 3D understanding. The model uses an 8-codebook fully-discrete visual representation built on AToken. Checkpoints are provided for Huawei Ascend NPUs and NVIDIA GPUs under Apache 2.0, with the technical report still listed as coming soon.

Why it matters: The model unifies text, image, video, and 3D understanding with image generation in one framework, a broader scope than single-modality releases.

AIOpenClaw 2.0 is an open-source, self-hosted AI agent harness whose update simplifies installation, rebuilds the browser interface, and adds shared cloud sessions for multiple users. The article says the patch notes state shared session controls are not a security boundary, secret store values are not encrypted at rest, and sandboxing is off by default.

AIAmazon Science explains Verus, an open-source automated program verifier for Rust that checks code against formal specifications for all possible inputs. Developers write specifications and proofs directly in Rust source using Rust-like syntax, and Verus returns feedback in under a second. Amazon says it has used Verus to prove the correctness of key primitives in the Nitro Isolation Engine and other infrastructure.

AIDeepSeek introduces DeepSeek-V4-Flash-Vision-Exp, its first experimental multimodal model in the DeepSeek-V4 family, built on V4-Flash with visual modules. It reports substantial gains over DeepSeek-V4-Flash-0731 on multimodal agent benchmarks, such as ApexBench at 36.5 versus 26.2, while keeping text agent performance comparable. The repository provides tokenizer files, prompt encoding, vLLM and SGLang serving instructions, and is licensed under MIT.

Why it matters: The source compares the model with its text-only predecessor and Opus-4.8 on agent benchmarks, showing where vision gains occur and where text performance holds.

AIAlibaba-NLP has published Core-Reranker-8B on Hugging Face, an 8B-parameter multimodal reranker fine-tuned from Qwen3-VL-Reranker to better distinguish attribute-object bindings in text and image relevance scoring. On compositional reasoning benchmarks COLA, SugarCrepe++, and NegBench, it reports an 82.7% total average, 10.7 points above Jina-Reranker. The model is part of the Core-Embed family, which also includes 2B and 8B embedding models, with Core-Embed-8B reporting a 0.666 total average.

AIAlibaba NLP has released core-emb-2b and core-emb-8b, multimodal embedding models built on Qwen3-VL that distill reranker judgments to better match attribute-object bindings in text and image retrieval. The Core-Embed-8B model posts the best total average (0.666) among evaluated embedding models on compositional benchmarks, 5.7 points above its VL-Emb-8B backbone. Companion Core-Reranker-2B and 8B models are also available, with the 8B reranker reaching 82.7% total average on the same benchmarks.

AIFunAudioLLM has released Fun-ASR-Nano-2512-vllm, a vLLM-native packaging of the official Fun-ASR-Nano-2512 checkpoint, with weights bitwise equal to the source and no new LoRA weights. The validated path runs on vLLM 0.27.1 with float32 through an OpenAI-compatible transcription endpoint, tested on one NVIDIA H100 80 GB GPU. The source-licensed model is Apache License 2.0, and other vLLM versions, accelerators, and quantizations require separate validation.

AIUnsloth quantized GLM-5.3 to a dynamic 1-bit version of 217GB, versus 1.5TB for BF16, retaining about 76% top-1 accuracy while cutting size by 83%. The team said a 1-bit build ran a simple snake game well in Unsloth Desktop. The post credits Z.ai's GLM-5.3-Flash and GLM-5.3 releases.

AIUnsloth AI published a guide for running GLM-5.3 locally using quantized GGUF weights. The 2-bit version is reduced from 1.51TB to 239GB and retains about 81% accuracy, and it can run on a 256GB Mac or RAM/VRAM setups.

Why it matters: The guide shows which quantization levels fit local memory budgets and how much accuracy each costs, useful for planning a local deployment.

AILM Studio says Zhipu's GLM-5.3 is now available in its Bionic agent, hosted in the US with zero data retention. The launch offer is 50% off until Monday. The post builds on Z.ai's announcement that GLM-5.3 is now open-weight for agentic coding and cyber defense.

AIZ.ai has made GLM-5.3 open-weight, so users can download, run, and customize its weights. The company describes it as its most capable model for agentic coding and cyber defense, with weights on Hugging Face and details in a tech blog.

AIMiniMax-H3 on 8×H200 GPUs reaches 1.85–1.95x lossless speedup over Diffusers without approximation, with fixed prompts, seeds, resolution, FPS, and 50 denoising steps. Adding step reuse and sparse attention raises speedup to as much as 6.24x, but quality varies by workload, with SSIM from 0.76 to 0.91. Two presets trade off the two: a conservative Cache-DiT setting gives 2.99x at 0.90–0.98 SSIM, while a faster SubBlock 0.75 plus Cache-DiT stride gives 4.90–5.93x at 0.77–0.92.

AIVercel has open-sourced vgpu.sh, a minimal, agent-first WebGPU library for shipping shaders on Vercel. It can run in the browser or headless in Node.js, render in CPU sandboxes and CI tests, and create reusable .wgsl modules.

AIGLM-5.3-Flash (ox-alpha) can be quantized to 4-bit while retaining 93% accuracy, according to Daniel Han. The post says the 4-bit model runs on a 256GB Mac or two DGX Sparks, and 5-bit may also work. Unsloth separately says 3-bit GGUF runs on 128GB RAM and that the model rivals Claude Opus 4.8 on DeepSWE, coding, and agentic benchmarks.

AIUnsloth says GLM-5.3-Flash can run locally, with a 3-bit GGUF version needing 128GB of RAM and the 1-bit version working on 102GB of RAM or VRAM. The guide's table lists memory needs from 100GB at 1-bit to 650GB at BF16, and reports that the 1-bit quant keeps 71% of top-1% accuracy while being 85% smaller than BF16.

Why it matters: The guide gives concrete memory requirements for each quantization level, which helps readers judge whether the model fits their hardware.

AIPollen Robotics has unveiled Microduck, a 25 cm open-source biped with 15 actuators and sensors including a camera, speaker, and LiDAR that users can train with reinforcement learning. The robot ships with more than half a dozen pre-trained policies for walking, sitting, roller-skating, and picking up objects with its articulated beak, and costs less than $400.

AITencent's Hy Team released Hy4 preview, a Mixture-of-Experts model with 770B total parameters and 49B activated per token, with a 1M context length. Hugging Face hosts the Instruct model and an FP8 quantized version under the Apache License 2.0, with vLLM and SGLang deployment instructions provided.

Why it matters: The model card gives architecture, activated parameters, and vLLM and SGLang deployment recipes, useful for judging whether the release fits your serving setup.

AIQwen has published Qwen-Drive-1.0-4B on Hugging Face, a vision-language model for autonomous driving built on Qwen3.5-4B. The release includes a BEV perception head and two Planning Experts, planner-sft and planner-rl, with code and an inference example in the linked GitHub repository.

Why it matters: The source gives concrete benchmark results and a runnable setup, letting readers judge how a driving VLM with planning and perception heads compares with existing systems.

AIZ.ai announced that the weights for GLM-5.3 will be released tomorrow. The post links to the GLM-5.3 model page on Hugging Face.

AITencent has published ContextPilot-E4B on Hugging Face, the Gemma4-E4B checkpoint of ContextPilot, a framework that teaches long-horizon language-model agents to plan, maintain long-term memory, and offload less useful context while reasoning and using tools. The checkpoint is intended for research on proactive context management, long-context QA, and deep search, and loading it alone does not execute the context-management tools, which are provided in the ContextPilot repository.

AITencent has released ContextPilot-14B on Hugging Face, a Qwen3-14B checkpoint for proactive context management in long-horizon language-model agents. The framework lets agents plan, maintain long-term memory, and offload less useful context while reasoning and using tools. The checkpoint is intended for research on long-context QA and deep search, and loading it alone does not execute the context-management tools, which are provided in the ContextPilot repository.

AIModel page:

AIHugging Face says it uses Inkling-Small to turn paper abstracts into quick, useful summaries. The post frames the work as open weights combined with open science, but gives no further details on the model's size, benchmarks, or availability.