It's been a few months but I didn't see a noticeable speed difference tbh. Otherwise, Ollama has usually a nice set of quantized models and easy to switch.
OPEN SOURCE
-
DeepSeek uses open-perfectblend dataset to train DSpark drafter
By
–
Fun surprise: DeepSeek used my open-perfectblend dataset to train their new DSpark drafter Time to promote it again! It's an open-source reproduction of "The Perfect Blend" paper. If you ever need >1M diverse prompts in math, chat, and code, it does the job.
-
hf-claude lets you use over 100 open models in Claude Code
By
–
hf-claude lets you use over 100 open models in claude code including glm 5.2, minimax-m3, deepseek v4 pro
-
LMCache offloads KV cache to CPU, disk, or S3 instead of evicting
By
–
Compression is one way to fight the KV cache wall. The other is to not throw the KV away. LMCache reuses and offloads it to CPU, disk, or S3 instead of evicting. Already plugs into vLLM, SGLang, and NVIDIA Dynamo. Worth a star if you serve LLMs.
-
Skepticism about OSS owning high-end model hardware
By
–
Those of you who are putting all your hope in OSS – you really think that if they are serious about all of this they’ll let you own the hardware that can run the top end models?
-
@dfintelligence — 2026-06-27
By
–
ATTENTION !!!! Ce serait une très grave erreur de se priver des modèles open source chinois ultra-performants en France. Des réponses orientées ou biaisées, oui, il y en a. Oui, il y en aura. Il y en en a aussi chez Mistral AI, GPT, Anthropic, etc. La probabilité qu'un agent
-
Reuse of Chat, Math, Code categories in open-perfectblend dataset
By
–
Wow, they really reused the three main categories Chat / Math / Code as well https://
huggingface.co/datasets/mlabo
nne/open-perfectblend
… -
Anthropic’s $1T valuation threatened by free GLM 5.2
By
–
Wanna know why Anthropic hates Opensource AI? GLM 5.2 being free and available to download made their $1 Trillion valuation make no sense
-
Frontier models improve but insufficient for reliable medical use
By
–
Thanks for running our open-source work on current frontier models “The results are: the most capable models today (GPT-5.5 Pro) did outperform the best models from before (79/100 vs 69/100), but did not improve enough to be considered sufficient for reliable medical use.” Read
-
Streaming 3D reconstruction from single camera, real-time, open-source
By
–
🚨 Forget LIDAR.
— Charly Wargnier (@DataChaz) 27 juin 2026
The Robbyant team just dropped a streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences.
One single camera. Runs in real time. Open-source.
Entirely end-to-end.
NO iterative optimization tricks and no post-processing cleanup steps!… pic.twitter.com/zo8GuGQYdIForget LIDAR. The Robbyant team just dropped a streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. One single camera. Runs in real time. Open-source. Entirely end-to-end. NO iterative optimization tricks and no post-processing cleanup steps!