corpus.blog
56,966 blogs · [ { "id": "01a0bb4e-6faf-71e2-a0ab-e23f443c0ced", "title": "Splash Engine - the fastest local Qwen3.8 on Apple Silicon", "url": "https://lmstudio.ai/blog/splash-engine", "published_at": "2026-09-18T00:00:00+00:00" }, { "id": "01a0bb4e-6faf-71e2-a0ab-e23f448366ce", "title": "Session References and Introspection", "url": "https://lmstudio.ai/blog/introducing-introspection", "published_at": "2026-09-17T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253265f7dfc4", "title": "How Auto Review works in Bionic", "url": "https://lmstudio.ai/blog/how-auto-review-works", "published_at": "2026-08-27T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532669ed2a4", "title": "Bionic now supports skills", "url": "https://lmstudio.ai/blog/skills", "published_at": "2026-08-17T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253267410ac5", "title": "Run Muse Glimmer locally", "url": "https://lmstudio.ai/blog/muse-glimmer", "published_at": "2026-08-10T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532676219be", "title": "Create slides and documents using Kimi K3 in Bionic", "url": "https://lmstudio.ai/blog/kimi-k3-bionic-documents-slides", "published_at": "2026-08-04T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253267c9ea27", "title": "Run DeepSeek V4 Flash locally or in the cloud (US-hosted)", "url": "https://lmstudio.ai/blog/deepseek-v4-flash", "published_at": "2026-08-02T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253268c43ab4", "title": "Run Kimi K3 in LM Studio Bionic", "url": "https://lmstudio.ai/blog/kimi-k3", "published_at": "2026-07-27T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253269755cf1", "title": "Introducing LM Studio Bionic: the AI agent for open models", "url": "https://lmstudio.ai/blog/introducing-lm-studio-bionic", "published_at": "2026-07-16T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253269c9d6f6", "title": "Improving LM Studio's MLX Engine for Agentic Workflows", "url": "https://lmstudio.ai/blog/mlx-engine-agentic-workloads", "published_at": "2026-06-05T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253269dd921f", "title": "Run (your largest) local models from your iPhone", "url": "https://lmstudio.ai/blog/locally-lm-link", "published_at": "2026-06-04T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326aad3d0e", "title": "Locally AI joins LM Studio", "url": "https://lmstudio.ai/blog/locally-ai-joins-lm-studio", "published_at": "2026-04-08T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326b70df1c", "title": "Run open models on NVIDIA DGX Station GB300", "url": "https://lmstudio.ai/blog/dgx-station", "published_at": "2026-03-18T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326c235d73", "title": "Use your LM Studio Models in Claude Code", "url": "https://lmstudio.ai/blog/claudecode", "published_at": "2026-01-30T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326cccf948", "title": "Introducing LM Studio 0.4.0", "url": "https://lmstudio.ai/blog/0.4.0", "published_at": "2026-01-28T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326dca49ba", "title": "Open Responses with local models via LM Studio", "url": "https://lmstudio.ai/blog/openresponses", "published_at": "2026-01-15T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326dd8bde3", "title": "LM Studio 0.3.37", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.37", "published_at": "2026-01-06T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326e388f0b", "title": "LM Studio 0.3.38", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.38", "published_at": "2026-01-06T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326ebb3441", "title": "How to fine-tune FunctionGemma and run it locally", "url": "https://lmstudio.ai/blog/functiongemma-unsloth", "published_at": "2025-12-23T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326ee0a0be", "title": "LM Studio 0.3.36", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.36", "published_at": "2025-12-18T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326ee24f8a", "title": "LM Studio 0.3.35", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.35", "published_at": "2025-12-12T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25326f68d16f", "title": "LM Studio 0.3.34", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.34", "published_at": "2025-12-10T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253270105558", "title": "Ministral 3", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.33", "published_at": "2025-12-02T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253270694fd9", "title": "LM Studio 0.3.32", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.32", "published_at": "2025-11-19T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532713aec88", "title": "LM Studio 0.3.31", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.31", "published_at": "2025-11-04T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253272310fa9", "title": "OpenAI gpt-oss-safeguard", "url": "https://lmstudio.ai/blog/gpt-oss-safeguard", "published_at": "2025-10-29T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253272a7888e", "title": "NVIDIA DGX Spark", "url": "https://lmstudio.ai/blog/dgx-spark", "published_at": "2025-10-14T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253272f3793e", "title": "LM Studio 0.3.30", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.30", "published_at": "2025-10-08T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253273e8f426", "title": "Use OpenAI's Responses API with local models", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.29", "published_at": "2025-10-06T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327415fcfd", "title": "LM Studio 0.3.28", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.28", "published_at": "2025-10-01T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532742a5868", "title": "LM Studio 0.3.27: Find in Chat and Search All Chats", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.27", "published_at": "2025-09-24T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253274a2d523", "title": "LM Studio 0.3.26", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.26", "published_at": "2025-09-15T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532757e8417", "title": "LM Studio 0.3.25", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.25", "published_at": "2025-09-04T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532761a1f63", "title": "LM Studio 0.3.24", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.24", "published_at": "2025-08-28T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532762e8d51", "title": "LM Studio 0.3.23", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.23", "published_at": "2025-08-12T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532771b53a6", "title": "Run OpenAI's gpt-oss locally in LM Studio", "url": "https://lmstudio.ai/blog/gpt-oss", "published_at": "2025-08-05T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327723af3c", "title": "LM Studio 0.3.20", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.20", "published_at": "2025-07-23T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532778a619a", "title": "LM Studio 0.3.19", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.19", "published_at": "2025-07-21T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327836b50a", "title": "LM Studio 0.3.18", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.18", "published_at": "2025-07-10T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253278680d86", "title": "LM Studio is free for use at work", "url": "https://lmstudio.ai/blog/free-for-work", "published_at": "2025-07-08T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253278eeff58", "title": "MCP in LM Studio", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.17", "published_at": "2025-06-25T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532791a5674", "title": "Introducing the unified multi-modal `MLX` engine architecture in LM Studio", "url": "https://lmstudio.ai/blog/unified-mlx-engine", "published_at": "2025-05-30T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327986ad36", "title": "DeepSeek-R1-0528 you can run on your computer", "url": "https://lmstudio.ai/blog/deepseek-r1-0528", "published_at": "2025-05-29T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327a23d52c", "title": "LM Studio 0.3.16", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.16", "published_at": "2025-05-23T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327ab9b2cd", "title": "LM Studio 0.3.15: RTX 50-series GPUs and improved tool use in the API", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.15", "published_at": "2025-04-24T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327b834ade", "title": "LM Studio 0.3.14: Multi-GPU Controls 🎛️", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.14", "published_at": "2025-03-27T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327c4d58eb", "title": "LM Studio 0.3.13: Google Gemma 3 Support", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.13", "published_at": "2025-03-12T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327c933146", "title": "LM Studio 0.3.12", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.12", "published_at": "2025-03-07T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327d228f73", "title": "Introducing `lmstudio-python` and `lmstudio-js`", "url": "https://lmstudio.ai/blog/introducing-lmstudio-sdk", "published_at": "2025-03-03T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327d774fed", "title": "LM Studio 0.3.11", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.11", "published_at": "2025-03-03T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327dde1a23", "title": "LM Studio 0.3.10: 🔮 Speculative Decoding", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.10", "published_at": "2025-02-18T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327e21281a", "title": "LM Studio 0.3.9", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.9", "published_at": "2025-01-30T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327ef2247a", "title": "DeepSeek R1: open source reasoning model", "url": "https://lmstudio.ai/blog/deepseek-r1", "published_at": "2025-01-29T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25327fc977c8", "title": "LM Studio 0.3.8", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.8", "published_at": "2025-01-21T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253280c0ec0a", "title": "LM Studio 0.3.7", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.7", "published_at": "2025-01-20T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532813d641b", "title": "LM Studio 0.3.6", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.6", "published_at": "2025-01-06T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253281d768a4", "title": "Introducing `venvstacks`: layered Python virtual environments", "url": "https://lmstudio.ai/blog/venvstacks", "published_at": "2024-10-31T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532821bbabb", "title": "LM Studio 0.3.5", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.5", "published_at": "2024-10-22T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25328316de26", "title": "LM Studio 0.3.4 ships with Apple MLX", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.4", "published_at": "2024-10-08T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532840a7033", "title": "LM Studio 0.3.3", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.3", "published_at": "2024-09-30T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253284b77c53", "title": "LM Studio 0.3.2", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.2", "published_at": "2024-08-27T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253285a166a4", "title": "LM Studio 0.3.1", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.1", "published_at": "2024-08-23T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-25328666ef37", "title": "LM Studio 0.3.0", "url": "https://lmstudio.ai/blog/lmstudio-v0.3.0", "published_at": "2024-08-22T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-2532873975b8", "title": "Llama 3.1", "url": "https://lmstudio.ai/blog/llama-3.1", "published_at": "2024-07-23T00:00:00+00:00" }, { "id": "01a07df3-df3d-701f-ae4b-253287df1964", "title": "Introducing `lms`: LM Studio's CLI", "url": "https://lmstudio.ai/blog/lms", "published_at": "2024-05-02T00:00:00+00:00" } ] posts Claim your blog
Back to LM Studio Blog
Blog · corpus.blog/blogs/lmstudio.ai/posts

LM Studio Blog

lmstudio.ai

2026

Splash Engine - the fastest local Qwen3.8 on Apple Siliconoriginal ↗
18 Sept 2026
Session References and Introspectionoriginal ↗
17 Sept 2026
How Auto Review works in Bionicoriginal ↗
27 Aug 2026
Bionic now supports skillsoriginal ↗
17 Aug 2026
Run Muse Glimmer locallyoriginal ↗
10 Aug 2026
Create slides and documents using Kimi K3 in Bionicoriginal ↗
4 Aug 2026
Run DeepSeek V4 Flash locally or in the cloud (US-hosted)original ↗
2 Aug 2026
Run Kimi K3 in LM Studio Bionicoriginal ↗
27 Jul 2026
Introducing LM Studio Bionic: the AI agent for open modelsoriginal ↗
16 Jul 2026
Improving LM Studio's MLX Engine for Agentic Workflowsoriginal ↗
5 Jun 2026
Run (your largest) local models from your iPhoneoriginal ↗
4 Jun 2026
Locally AI joins LM Studiooriginal ↗
8 Apr 2026
Run open models on NVIDIA DGX Station GB300original ↗
18 Mar 2026
Use your LM Studio Models in Claude Codeoriginal ↗
30 Jan 2026
Introducing LM Studio 0.4.0original ↗
28 Jan 2026
Open Responses with local models via LM Studiooriginal ↗
15 Jan 2026
LM Studio 0.3.37original ↗
6 Jan 2026
LM Studio 0.3.38original ↗
6 Jan 2026

2025

How to fine-tune FunctionGemma and run it locallyoriginal ↗
23 Dec 2025
LM Studio 0.3.36original ↗
18 Dec 2025
LM Studio 0.3.35original ↗
12 Dec 2025
LM Studio 0.3.34original ↗
10 Dec 2025
Ministral 3original ↗
2 Dec 2025
LM Studio 0.3.32original ↗
19 Nov 2025
LM Studio 0.3.31original ↗
4 Nov 2025
OpenAI gpt-oss-safeguardoriginal ↗
29 Oct 2025
NVIDIA DGX Sparkoriginal ↗
14 Oct 2025
LM Studio 0.3.30original ↗
8 Oct 2025
Use OpenAI's Responses API with local modelsoriginal ↗
6 Oct 2025
LM Studio 0.3.28original ↗
1 Oct 2025
LM Studio 0.3.27: Find in Chat and Search All Chatsoriginal ↗
24 Sept 2025
LM Studio 0.3.26original ↗
15 Sept 2025
LM Studio 0.3.25original ↗
4 Sept 2025
LM Studio 0.3.24original ↗
28 Aug 2025
LM Studio 0.3.23original ↗
12 Aug 2025
Run OpenAI's gpt-oss locally in LM Studiooriginal ↗
5 Aug 2025
LM Studio 0.3.20original ↗
23 Jul 2025
LM Studio 0.3.19original ↗
21 Jul 2025
LM Studio 0.3.18original ↗
10 Jul 2025
LM Studio is free for use at workoriginal ↗
8 Jul 2025
MCP in LM Studiooriginal ↗
25 Jun 2025
Introducing the unified multi-modal `MLX` engine architecture in LM Studiooriginal ↗
30 May 2025
DeepSeek-R1-0528 you can run on your computeroriginal ↗
29 May 2025
LM Studio 0.3.16original ↗
23 May 2025
LM Studio 0.3.15: RTX 50-series GPUs and improved tool use in the APIoriginal ↗
24 Apr 2025
LM Studio 0.3.14: Multi-GPU Controls 🎛️original ↗
27 Mar 2025
LM Studio 0.3.13: Google Gemma 3 Supportoriginal ↗
12 Mar 2025
LM Studio 0.3.12original ↗
7 Mar 2025
Introducing `lmstudio-python` and `lmstudio-js`original ↗
3 Mar 2025
LM Studio 0.3.11original ↗
3 Mar 2025
LM Studio 0.3.10: 🔮 Speculative Decodingoriginal ↗
18 Feb 2025
LM Studio 0.3.9original ↗
30 Jan 2025
DeepSeek R1: open source reasoning modeloriginal ↗
29 Jan 2025
LM Studio 0.3.8original ↗
21 Jan 2025
LM Studio 0.3.7original ↗
20 Jan 2025
LM Studio 0.3.6original ↗
6 Jan 2025

2024

Introducing `venvstacks`: layered Python virtual environmentsoriginal ↗
31 Oct 2024
LM Studio 0.3.5original ↗
22 Oct 2024
LM Studio 0.3.4 ships with Apple MLXoriginal ↗
8 Oct 2024
LM Studio 0.3.3original ↗
30 Sept 2024
LM Studio 0.3.2original ↗
27 Aug 2024
LM Studio 0.3.1original ↗
23 Aug 2024
LM Studio 0.3.0original ↗
22 Aug 2024
Llama 3.1original ↗
23 Jul 2024
Introducing `lms`: LM Studio's CLIoriginal ↗
2 May 2024