AICoder

AI Coding Live News

First-hand AI coding updates from 𝕏/Twitter frontier labs and researchers, distilled by AI with entity benchmarks.

Explore live on 𝕏 ↗

AI Coding Live News

L
LM Studiolmstudio·
👀82
🔥80
View on 𝕏 ↗

LM Studio Bionic 1.1.10 adds the oMLX engine, bringing RAM-plus-SSD KV caching and MLX speculative decoding to local models on Macs

LM Studio posted on X at 15:32 UTC on Oct 29 that users can now download a new oMLX engine inside LM Studio and run it with MLX models they already have. The official changelog lists it in Bionic 1.1.10, alongside speculative decoding for MLX models and an in-app terminal. oMLX is an open-source Apple Silicon inference server maintained by developer jundot (Apache 2.0, about 23,000 GitHub stars) built around continuous batching and a two-tier RAM and SSD KV cache. LM Studio has not published speed comparisons for the engine.

LM Studio Bionic 1.1.10 adds the oMLX engine, bringing RAM-plus-SSD KV caching and MLX speculative decoding to local models on Macs

Key Takeaways

  • LM Studio says the oMLX engine can now be downloaded inside the app and used with existing MLX models; the post has about 540 likes (post)
  • The Bionic 1.1.10 changelog (Oct 29) also lists speculative decoding for MLX models, a public in-app terminal and llama.cpp 2.66.0 extension packs (changelog)
  • oMLX is Apache 2.0 open source with about 23,000 GitHub stars and needs macOS 15+ on Apple Silicon M1 to M5 (GitHub)
  • Its core is a two-tier KV cache: hot blocks stay in RAM, overflow is written to SSD as safetensors, and matching prefixes are restored from disk even after a restart
  • LM Studio has published no speed comparison with its existing MLX engine; one user reported that restart-to-update failed after launch and LM Studio is investigating
Read full story
Linked Models & Agents:
⚡ MLX🤖 LM Studio🤖 oMLX🌐 LM Studio🌐 Hugging Face🌐 Apple
#LM Studio#oMLX#MLX#Apple Silicon#local LLM#KV cache#inference engine
C
Cline@cline·
👀108
🔥88

Cline v4.1.21: ai& Japan OpenAI-compatible provider, 6,386 models / 209 providers, local long-reply compact retry

Cline VS Code extension shipped v4.1.21 on 2026-09-24 with a new Japan OpenAI-compatible provider (ai&), a refreshed catalog of 6,386 models across 209 providers (19 unpinned defaults change—11 to Claude Opus 5.5 including GitHub Copilot and Vertex), and compact-and-retry once when local servers (llama.cpp/Ollama/LM Studio) hit output-token limits. Minimum js-yaml raised to 4.3.2 for frontmatter parsing security.

Cline v4.1.21: ai& Japan OpenAI-compatible provider, 6,386 models / 209 providers, local long-reply compact retry

Key Takeaways

  • New provider ai& (Japan OpenAI-compatible open-weight endpoint)
  • Catalog: 6,386 models / 209 providers; 19 unpinned defaults shift (11 → Opus 5.5 incl. Copilot & Vertex)
  • Local models compact-and-retry once on output-token caps
  • js-yaml floor 4.3.2 for rule/skill frontmatter
  • Install via Marketplace or cline-4.1.21.vsix
Read full story
Linked Models & Agents:
⚡ Claude Opus 5.5🤖 Cline🌐 Cline🌐 ai&🌐 GitHub Copilot🌐 Vertex
#Cline#VS Code#ai&#model catalog#Ollama#llama.cpp#Opus 5.5
L
LM Studio@lmstudio·
👀66
🔥87
View on 𝕏 ↗

LM Studio: Bionic agent gains session introspection and @ mentions across sessions

LM Studio (@lmstudio) introduced Introspection and Session References for its Bionic agent: the agent can search its own session history to stay useful after many compactions, and the composer lets you @-mention other sessions to continue work across chats.

Key Takeaways

  • Bionic agent can search its own session history after many compactions.
  • Composer @-mentions let you reference other sessions directly.
  • A local LM Studio agent-workflow upgrade, not a new model drop.
Read full story
Linked Models & Agents:
🤖 bionic🤖 lm-studio🌐 lmstudio
#LM Studio#Bionic#session history#Introspection#Compaction#local LLM
L
LM Studio@lmstudio·
👀118
🔥94
View on 𝕏 ↗

LM Studio ships Inco Splash day 0: ~144 tok/s Qwen3.8-27B on M5 Max

LM Studio announced a day-0 partnership with Inco to bring the Splash inference engine into LM Studio. They cite up to about 144 tok/s for Qwen3.8-27B on M5 Max, with setup docs at lmstudio.ai/blog/splash-engine. Splash was already open-sourced by Inco; this puts the Apple-silicon-optimized stack inside LM Studio so local desktop users do not have to assemble the engine separately.

Key Takeaways

  • LM Studio integrates Inco Splash on day 0 for one-click local desktop use.
  • Claims ~144 tok/s for Qwen3.8-27B on M5 Max, with an official setup post.
  • Moves Apple-silicon-optimized inference into a mainstream local client distribution path.
Read full story
Linked Models & Agents:
⚡ Qwen3.8-27B🌐 lm-studio🌐 inco
#LM Studio#Splash#Inco#Qwen3.8#Apple Silicon#local inference#M5 Max
ADSponsored
I
Inco AI@inco_ai·
👀203
🔥93
View on 𝕏 ↗

Inco open-sources Splash: ~144 tok/s for Qwen3.8-27B on M5 Max

Inco AI open-sourced Splash, a local inference engine built for Apple silicon and models like Qwen3.8-27B. On an M5 Max MacBook Pro it reports about 144 tok/s—up to 3× Ollama, 2× oMLX, and nearly 4× when an agent fans out sub-agents. LM Studio shipped day-0 support under Settings > Runtime > Experimental backends.

Key Takeaways

  • Open-source Splash: local inference tuned for Apple silicon and Qwen3.8-27B.
  • Demo: ~144 tok/s on M5 Max; up to ~3× Ollama / 2× oMLX, nearly 4× with agent fan-out.
  • LM Studio day-0 support; repo github.com/incoai/splash; blog lmstudio.ai/blog/splash-engine.
Read full story
Linked Models & Agents:
⚡ Qwen3.8-27B🌐 inco🌐 Qwen (通义千问)🌐 lmstudio
#Inco#Splash#Qwen3.8-27B#Apple Silicon#M5 Max#LM Studio#local inference#open source
L
LM Studio@lmstudio·
👀57
🔥86
View on 𝕏 ↗

LM Studio Launches Bionic Auto Review to Automate 82% of Agent Shell Execution Permissions

LM Studio introduced Bionic Auto Review for automated agent shell tool permissions, combining AST parsing and deterministic command matching to auto-approve 82% of safe terminal requests.

Key Takeaways

  • Automates tedious human-in-the-loop click confirmations for safe routine terminal commands;
  • Two-tier defense in depth: deterministic AST grammar verification followed by an LLM reviewer subagent;
  • Accelerates autonomous multi-step coding agent loops while safeguarding local operating system integrity.
Read full story
Linked Models & Agents:
H
Hugging Face@huggingface·
👀109
🔥93
View on 𝕏 ↗

Hugging Face Releases State of Open Models Report: Qwen Series Leads Global Local Inference Ecosystem

Hugging Face published its Summer 2026 State of Open Models report, highlighting Alibaba Qwen's dominance in on-device deployment and developer tooling, accounting for over 40% of local open-model inference.

Key Takeaways

  • Alibaba Qwen captures over 40% market share across local tooling and on-device developer environments;
  • Quantization advances and sparse attention enable long-horizon agent execution on consumer GPUs;
  • SWE-bench performance gap between open weights and closed frontier models narrowed to under six months.
Read full story
Linked Models & Agents:
⚡ Qwen3.8-Flash⚡ Qwen 2.5 Coder 32B
You've caught up with all stories