ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode
AI model

Qwen3.6-35B-A3B

2 mentions in 7 days · 3 in 30 days · 3 total · first seen · last

Search everything

Timeline

Best Open-Source Agent Harnesses for Local LLMs in 2026

A 2026 guide ranks 11 open-source agent harnesses, including OpenCode, Goose, Cline, and OpenHands, by local-LLM support, licensing, and safety controls.

The guide ranks 11 open-source LLM agent harnesses by OSI license, documented local runtimes, maintenance status, and safety controls, using GitHub data read September 18, 2026. OpenCode documents Ollama, LM Studio, and llama.cpp setups across 75+ providers; Pi offers a minimal four-tool harness and was acquired by Earendil in April 2026; Goose is Rust-based with 70+ MCP extensions under the Linux Foundation's Agentic AI Foundation. Cline defaults to per-action approvals, while OpenHands recommends Qwen3.6-35B-A3B with at least 24GB VRAM and 32,768-token context.

MarkTechPost · 6h agoAI tools & infra

[AINews] not much happened today

Latent Space AI news digest covers Anthropic's Claude Code Projects, Google's managed agent APIs, TypeSafe's Jev classifier, and OpenAI's Astra for Law launch.

The 9/16-9/17/2026 AI news roundup highlights Anthropic's Claude Code Projects enabling one conversation to spawn parallel cloud sessions, and Google's Gemini managed agents adding a Credentials API, Files API, and claims of 30% lower costs. It also covers TypeSafe's Jev, a fast constrained-output classifier being used for routing, judgment, and structured decisions, with open reproductions such as openjev-s on Qwen3.6-35B-A3B. OpenAI launched Astra for Law with 26 partner-built and 47 community plugins via Trusted Access, with reports it beats generic GPT-6 Astra plus web search on Vals' legal benchmark. Research items include DeepMind's Stellar Colosseum multi-agent math harness (Codeforces 4263, 71.0% on TCS-Bench) and NVIDIA-associated Agora using Git commits as shared memory.

Latent Space · 9h agoAI industry 2 sources

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF — new model trending #30 on Hugging Face

DavidAU releases Qwen3.8-27B-TWIN-TURBO, an uncensored GGUF fine-tune claiming sharply reduced thinking tokens and self-reported benchmark gains.

A new community fine-tune of Qwen3.8-27B, built with Unsloth via 'Cold Fusion' and 'Fable Fusion 711' methods, is trending #30 on Hugging Face. The author claims arc-c scores of 709 in 8-bit and 701 in 4-bit, exceeding the base Qwen3.8-27B, while cutting thinking tokens to between 1/2 and 1/20 of baseline. The release provides regular and MTP Neo/NEO MAX GGUF quants, five switchable reasoning modes plus five zero-reasoning instruct modes, and a lightly uncensored variant. All benchmark claims are author-reported and not independently verified.

Hugging Face trending models · 8d agoModel release

Appears with

ai model Qwen 3.5 27B 1ai model Qwen3.6-27B-Fable-Fusion-711 1ai model Qwen3.8-27B 1organization Earendil 1organization Hugging Face 1organization Latent Space 1organization Linux Foundation 1product Aider 1product Astra 1product Claude Code 1product Cline 1product Codex 1product Codex CLI 1product Gemini 1product Goose 1ai model GPT-6 Astra 1
Entities are extracted by the model from each article. Watching an entity keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.