We're excited to bring you Flint by @Recursive_SI in LM Studio on day 0!
• 40B MoE, 2.5B active
• 262K token context window
• Apache 2.0
• Trained for local agentic coding model
Requires about 24GB to run locally on your machine, performs impressively on benchmarks.
• 40B MoE, 2.5B active
• 262K token context window
• Apache 2.0
• Trained for local agentic coding model
Requires about 24GB to run locally on your machine, performs impressively on benchmarks.
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine.
• Best-in-class fast local coding
• Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
• Built from hs
Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
41
64
826
44,476
DeepSeek-V4.1-Flash-1017 is now live in LM Studio Bionic!
1M context • image input • highly cost effective
US-hosted with full ZDR.
Try it out for coding tasks!
1M context • image input • highly cost effective
US-hosted with full ZDR.
Try it out for coding tasks!
🚀 DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, grade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
14
21
367
19,879
Beam (501B MoE) by Reflection is now live in Bionic!
US-hosted and ZDR.
Let’s go! 🚀👾
US-hosted and ZDR.
Let’s go! 🚀👾
Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners.
We're releasing:
- Weights, tokenizer, and reference implementation
- BF16, FP8 and NVFP4 weights and a DFlash2 drafter
- The open source ained Beam on: Mirror CLI
Weights and model card on Hugging Face: huggingface.co/reflection
2
5
58
7,699
Nemotron 3.5 Super VL from @NVIDIAAI is live in LM Studio!
• 120B total / 12B active MoE
• Supports vision input, reasoning
• Trained for visual understanding, tool use
Requires ~70GB RAM to run locally 🚀 👾
lmstudio.ai/models/nemotro…
• 120B total / 12B active MoE
• Supports vision input, reasoning
• Trained for visual understanding, tool use
Requires ~70GB RAM to run locally 🚀 👾
lmstudio.ai/models/nemotro…
17
21
307
17,545
LM Studio retweeted
State → local decision model → action
Check out @liquidai's d1 decision model playing Lmmy Run, all on its own 🦖👾
Served 100% on-device, making decisions in a fraction of a second
Check out @liquidai's d1 decision model playing Lmmy Run, all on its own 🦖👾
Served 100% on-device, making decisions in a fraction of a second
6
27
296
20,091
LM Studio retweeted
LM Studio 0.4.26 is out now!
• ⚡️ `/v1/systemone` and `/v1/decisions` APIs
• 👾 Coexistence with Bionic
• 🎨 UI updates and bug fixes
Yes, you can now point your Bionic agent to models loaded in your LM Studio.
lmstudio.ai/docs/developer…
• ⚡️ `/v1/systemone` and `/v1/decisions` APIs
• 👾 Coexistence with Bionic
• 🎨 UI updates and bug fixes
Yes, you can now point your Bionic agent to models loaded in your LM Studio.
lmstudio.ai/docs/developer…
12
28
225
13,766
Also new in Bionic 1.1.8:
- /v1/systemone and /v1/decisions API support
- Run Bionic at the same as LM Studio
lmstudio.ai/changelog/bion…
- /v1/systemone and /v1/decisions API support
- Run Bionic at the same as LM Studio
lmstudio.ai/changelog/bion…
3
1
18
2,678
We’re so back.
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
14
14
681
34,649
Qwen3.8-27B, up to 144 tok/sec on M5 Max.
Let that sink in. ⚡️✨🚀
Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0!
Get it running now: lmstudio.ai/blog/splash-en…
Let that sink in. ⚡️✨🚀
Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0!
Get it running now: lmstudio.ai/blog/splash-en…
Qwen3.8-27B at 144 tok/s on an M5 Max MacBook Pro ⚡
Meet Inco Splash: our open-source inference engine, built around the model and around Apple silicon.
Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents.
75
135
1,728
227,779
The Splash engine is open source, check it out: github.com/incoai/splash
1
2
26
5,793