Introducing Cline Desktop - a native interface for working with open weights models.
Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Musespark-1.3, or BYOK with any provider!
Muse Ember by @AIatMeta is now in Cline!
A lightweight model that’s fast, low-cost, and purpose-built for subagent work like coding and document analysis.
We nearly doubled throughput for Nemotron 3.5 Super VL on a single GB300 GPU, from 6,058 → 11,840 tok/s, with five configuration changes in vLLM.
These let the model draft tokens ahead, keep the GPU from ever sitting idle, and store the model’s memory at half precision.
Gemini 4 Carbon is the first model to surpass Claude and GPT, and beats Opus 5.5 on nearly every benchmark at half the cost.
That’s an 18% improvement in only 2 weeks since Argon.
We teamed up with @composio and @p0 for a hackathon!
Teams had 3.5 hours to turn their personal agent ideas into working projects using Cline, and the results were incredible 🔥
Here's a recap of the event:
New in Cline Desktop v0.0.49 🧵
1) Install and manage local models through Ollama or LM Studio. Cline checks your hardware and recommends the best local models available.
Try via Settings → Provider → Local
Kimi K3.1 Pro nearly matches Opus 5.5 performance on Terminal-Bench 4.0 at *half* the cost.
Moonshot also removed cyber data from mid-training and RL to deliberately reduce performance on exploit tasks by ~10%, while everything else, including coding, kept improving.
There’s new free models available in Cline:
- Reflection Beam (501B)
- Nemotron 3.5 Super VL (120B)
- Poolside Laguna S 2.1 (118B)
- Nemotron 3.5 Lightning (32B)
- Solar Mini 4 (35B)
6 months ago these Terminal-Bench scores were frontier, open weights makes this more accessible.