Topic: Models Related concepts: Code Agents RAG Frequently mentioned with: Hugging Face NVIDIA OpenAI Google arXiv Recent briefs: 2026-11-10 2026-11-09 2026-11-08 2026-11-07 2026-11-06
Topic: Models Related: Code Agents RAG
Recent Updates
- 2026-11-03: Factorial Ablation Study on Compression Technique Interactions in Small Language Models (breakingnewsofficial) · arxiv.org
- 2026-11-03: ParallACT: Benchmarking Orchestrator-Free Multi-Agent Coding in Shared Codebases (breakingnewsofficial) · arxiv.org — Claude Opus 4.8
- 2026-11-03: MEMENTO: Learning Context Management and Compaction for Long-Context Agents (breakingnewsofficial) · arxiv.org — Qwen3-8B · GPT 5.5 · GLM-5.3
- 2026-11-03: Sebastian Raschka Releases LLM Architecture Gallery and Comparison Tool (breakingnewsofficial) · sebastianraschka.com — OpenAI · DeepSeek Gumroad Sebastian Raschka · GPT-2 · LLaMA-3 · LLaMA · OLMo-2 · Qwen · Qwen3 · DeepSeek-V3 · DeepSeek R1 · Gemma · Gemma-2
- 2026-11-04: DoGNAVY-Exploit: Parallel Multi-Agent Harness for Vulnerability Exploitation with Open-Weight Models (breakingnewsofficial) · arxiv.org — GLM-5.2 · GLM-5.3
- 2026-11-04: Dory1.0-4B: Elastic-Depth Looped Language Model with KV-Cache Memory Optimizations (breakingnewsofficial) · arxiv.org — Dory1.0-4B Qwen3.5-9B · Gemma 4 12B · Gemma-4-26B-A4B
- 2026-11-04: Reasoning History Compaction to Reduce Future Reasoning Cost in Open-Weight Models and Agents (breakingnewsofficial) · arxiv.org — arXiv
- 2026-11-04: Moonshot AI Releases Kimi K3.1 Pro Model Weights with 1M Context Window (breakingnewsofficial) · huggingface.co — Kimi.ai · Moonshot AI · Hugging Face · Google · Kaggle Encyclopaedia Britannica · Kimi K3.1 Pro · Kimi K3
- 2026-11-04: Moonshot AI Releases Kimi K3.1 Pro Weights with Gated DeepSeek Sparse Attention (breakingnewsofficial) · huggingface.co — Moonshot AI · Hugging Face · Google · Kaggle · Docker · LMSYS · Kimi K3.1 Pro · Kimi K3
- 2026-11-04: Moonshot AI Releases Kimi K3.1 Pro Open-Weight Multimodal Model (breakingnewsofficial) · huggingface.co — Moonshot AI · Hugging Face · Google · Kaggle · Docker · Kimi K3.1 Pro · Kimi K3
- 2026-11-04: Ricursive Intelligence Releases Ripple-65B Preview Open-Weight Coding Model (breakingnewsofficial) · ricursive.com — Hacker News Ricursive Intelligence · Meta · Thinking Machines · NVIDIA · Hugging Face · Together AI · GMI Cloud · OpenRouter · Fireworks · OpenAI Sam Altman Dario Amodei Ripple-65B Preview Reflection Beam 501B Meta Muse Spark Open 816B Thinking Machines Inkling 975B NVIDIA Nemotron 3 Ultra 550B · GPT-4
- 2026-11-05: Study of Reasoning-Token Overflow in Open-Source Code-Generation Models (breakingnewsofficial) · arxiv.org
- 2026-11-05: awesome-free-llm-apis: Curated Directory of Permanent Free LLM API Endpoints (breakingnewsofficial) · github.com — Aion Labs Cohere · Google · Mistral AI · Cloudflare Gonka Broker · Groq Kilo Code LLM7.io · ModelScope · Alibaba Cloud · NVIDIA · OpenRouter · OVHcloud · Siliconflow · GitHub
- 2026-11-05: Offline Survival Assistant Combines BM25 Search, Kiwix ZIM Files, and Local LLMs (breakingnewsofficial) · github.com — Wikipedia Kiwix WHO Red Cross IFRC AHA · CDC Hesperian · Qwen2.5-3B
- 2026-11-06: Village Study Finds Closed AI Models Lead Price-Performance Frontier Across Most Budgets (breakingnewsofficial) · village.dev — Village Google · Xiaomi · DeepSeek · Zhipu · OpenAI · Anthropic · Gemma 4 E4B · MiMo-V2.6-Flash · DeepSeek-V4-Flash · GLM-5.2 · GPT-6 Luna · GPT-6.1 Terra · Claude Haiku 5.5 · DeepSeek-v3.2-exp · Claude Opus 5.5 · GPT-6 GPT 6.1 · Sol · Astra · GPT-5
- 2026-11-06: PROMETHEVS Enables Running DeepSeek-V4.1-Flash Locally on 12GB VRAM (breakingnewsofficial) · github.com — OpenAI · NVIDIA · DeepSeek Ryan Flavell · DeepSeek-V4.1-Flash-1017
- 2026-11-07: Running Claude Code via a Custom Gateway on GLM-5.3 and Local Qwen (breakingnewsofficial) · habr.com — Anthropic ZuBrIQ · GLM-5.3 · Qwen3.8-27B
- 2026-11-08: MAPLE: Sub-2-BPW MoE Pruning to Run Gemma 4 26B on 6GB GPUs at 45 TPS (breakingnewsofficial) · github.com — Hugging Face Google Scholar Aman Sachan · gemma-4-26b · Gemma-4-26B-A4B
- 2026-11-09: Benchmarking Prompt Injection Guards on Legal Contract Review Attacks (breakingnewsofficial) · arxiv.org
- 2026-11-09: Thought Injection Attacks Exploit Reasoning Traces in Agentic Systems (breakingnewsofficial) · arxiv.org — arXiv · GLM-5.3 · MiniMax-M2.5 · Qwen3.8-Flash-Next
- 2026-11-09: Tencent Releases Hunyuan Hy4 with Multimodal Agent and Computer-Use Capabilities (breakingnewsofficial) · qbitai.com — Tencent · Peking University · QbitAI Wen Le Hunyuan Hy4
- 2026-11-10: Hibana: Fast Agentic Inference Engine for Unified-Memory Devices (breakingnewsofficial) · github.com — NVIDIA · Qwen · Nemotron
- 2026-11-10: Jais 3: Open Arabic-Centric Agentic Language Models Fleet (breakingnewsofficial) · arxiv.org — Jais 3 K2 Horizon
- 2026-11-10: PACE: Planner-Aware Context Engine for Long-Horizon LLM Agents (breakingnewsofficial) · arxiv.org — Qwen3-8B · Mistral-7B
- 2026-11-10: An Open Field Guide to Inference Engineering (breakingnewsofficial) · docs.modelplane.ai — Hacker News · Hugging Face · OpenAI · DeepSeek Upbound ByteByteGo Spheron Viktor Farcic Philip Kiely Vishakha Sadhwani Chris Zeoli · R1 · o1
FAQ
What is Open Source LLMs?
Open Source LLMs are language models released with weights, code, or permissive access that builders can inspect, fine-tune, or self-host. GROUNDING tracks open model releases, inference stacks, and benchmarks.
Which concepts are related to Open Source LLMs?
Related concepts tracked by the radar include Code Agents, RAG.
What does this Open Source LLMs page track?
Dated updates, papers, and mentions of Open Source LLMs collected by the GROUNDING radar, most recently on 2026-11-10.