
Open-source software/tools/datasets, news, research et al. regarding #machinelearning and #datascience, with a focus on #deeplearning.
Global
Joined February 2012
- Tweets3.9K
- Following828
- Followers8.2K
- Likes5.8K
DeepLearning.Hub retweeted
Run Inkling 2 Mini, the strongest 26.4B model that runs on 16GB RAM.
Thinking Machines’ Apache 2.0 MoE model uses a looped transformer arch & scores 48.2% on DeepSWE v1.1, the best for size.
Run on Unsloth, llama.cpp
GGUF: huggingface.co/unsloth/Inkli…
Guide: unsloth.ai/docs/models/inkli…
Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you: Inkling 2 Mini is a looped transformer with just 26B parameters, small enough to run on your laptop, powerful enough for agentic work with a score of 20.1 on AA Index.
thinkingmachines.ai/news/ink…
Introducing safeagents!
A lightweight proxy that scans in real time tool calls before they execute, and blocks the ones it sees as dangerous.
Supports also reward hacking detection for evals.
We also release a benchmark to assess decision models capabilities on this task - safeagents-judge-bench 🧵
Announcing harness adapters for @Alibaba_Qwen Qwen3.8-27B on Pi harness!
We're releasing a LoRA adapter that makes Qwen3.8-27B a much better and efficient agent behind Pi harness.
SWE-Bench Pro (Hard 51 subset) pass@1: 29% -> 63%
Terminal-Bench 2.1 pass@1: 40% -> 56%
Much more efficient: 55-62% fewer tool calls per task 🤯
huggingface.co/harness-hub/Q…
The era of harness-specific adapters is now on! More harness adapters to come in the next days 🧵
DeepLearning.Hub retweeted
We collaborated with @AMD to bring local model inference to AMD NPUs.
NPUs deliver powerful compute performance while using 2–4× less power than traditional GPUs.
We teamed up to enable running models with less power!
Strix, Gorgon, Krackan & more.
Blog: newsroom.amd.com/news/amd-un…
AMD XDNA 2 NPUs are the world's first NPUs supported by @UnslothAI Desktop. 100+ agentic apps. Now on your NPU. bit.ly/4jqlftF
DeepLearning.Hub retweeted
Introducing Qwen3.8-27B-pi-adapted 🤗
We adapted Qwen's model specifically for the pi coding agent using reinforcement learning and a LoRA adapter.
The results, measured as pass@1:
🚀 SWE-bench Pro (Hard 51): 29.4% → 62.7%
💻 Terminal-Bench 2.1: 39.5% → 55.8%
⚡ 55–62% fewer tool calls per task
This is the power of open models: you can adapt them to YOUR tools and YOUR use cases. Let’s build! 💛
Open weights: huggingface.co/harness-hub/Q…
Methodology: huggingface.co/blog/harness-…
DeepLearning.Hub retweeted
Unsloth now has computer use for any local model! It's still beta but we had Qwen3.8-27B make an expense report from receipts & used GIMP to scale photos, add captions & export it!
Also we added driving Unreal Engine, Blender & more to local models!
github.com/unslothai/unsloth…
DeepLearning.Hub retweeted
Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs.
Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on even better version for Qwen4
Run on 12GB RAM.
GGUF: huggingface.co/unsloth/Qwen3…
Blog: unsloth.ai/docs/models/qwen3…
DeepLearning.Hub retweeted
Happy to share 🧬 FineDNA, a multi-stage dataset to teach LLMs the meaning of life:
Mid-training: 300B+ tokens of genomic sequences, papers and web pages mixing DNA and text. Provides a bridge between the abstract DNA representations of genomic LLMs with the semantics of natural language.
SFT: 200k samples spanning DNA computation, sequence analysis, and variant effect prediction. Grounded in real DNA sequences with deterministic verifiers to prevent hallucinations.
RLVR: 100k calibrated samples to augment SFT and unlock hard-to-learn capabilities like localising a strand of DNA within a huge sequence.
Models trained on FineDNA can "chat with DNA" and match the performance of frontier models on DNA understanding tasks.
Dataset: huggingface.co/datasets/Hugg…
Code: github.com/huggingface/carbo…
Happy Halloween 👻!
DeepLearning.Hub retweeted
Your local LLM can now take control of a browser and complete tasks autonomously via Unsloth!
Qwen3.8-27B successfully controlled the browser to complete tasks like chess, painting, with no human intervention.
GitHub: github.com/unslothai/unsloth
Guide: unsloth.ai/docs/basics/brows…
DeepLearning.Hub retweeted
MiniMax-M3.1-Flash can now run locally!
We made 2-bit GGUF retain 91.5% top 1 accuracy while being 45% smaller. Run on 150GB RAM.
MiniMax-M3.1-Flash is the strongest open model for its size & among the best overall.
GGUF: huggingface.co/unsloth/MiniM…
Guide: unsloth.ai/docs/models/minim…
MiniMax M3.1 Flash: Space Performance + Bunny Speed
🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.
💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.
API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.
Model weights will arrive on Oct 23.
API: platform.minimax.io
M Plan: minimax.io/m-plan
MiniMax Code for desktop: agent.minimax.io/download
DeepLearning.Hub retweeted
We just launched OpenUSD support on the @huggingface Hub 🎉
Yesterday, @nvidiaomniverse put 2,500+ SimReady assets on the Hub. Forklifts, robot arms, engines, hospital equipment, all OpenUSD. You can also search the whole library in plain English
huggingface.co/spaces/nvidia…
huggingface.co/datasets/nvid…
DeepLearning.Hub retweeted
A Chinese job-recruitment app just released an open-weights 33B model that beats Qwen 27B on most agentic benchmarks.
Nanbeige is the research team of BOSS Zhipin (think WhatsApp meets LinkedIn).
Strong open models in China now come from labs, cloud providers, quant funds... and job boards. China's open-weights roster keeps getting deeper.
🚀Excited to announce Nanbeige4.3-33B!
To push the performance ceiling of small agents, our strategy in Nanbeige4.3 starts with building a powerful teacher first.
Nanbeige4.3-33B delivers SOTA agentic performance among open models at ~30B parameters:
* Strong results on agentic coding and cowork benchmarks.
* When integrated into mainstream agent harnesses, it tackles real-world tasks with cost-efficient inference.
* It will serve as a teacher for upcoming smaller Nanbeige models, starting with Nanbeige4.3-3B.
huggingface.co/Nanbeige/Nanb…
huggingface.co/Nanbeige/Nanb…
#LLM #Agent
DeepLearning.Hub retweeted
NVIDIA releases Nemotron-3.5-Bolt-E4B, a new model that runs locally on 6GB RAM. 💚
Bolt-E4B can run on edge devices like phones and delivers top-tier performance for its size. Trained on Gemma 4, it supports vision.
GGUF: huggingface.co/unsloth/NVIDI…
Guide: unsloth.ai/docs/models/nemot…
Available now: NVIDIA Nemotron 3.5 Bolt E4B 4GB ⚡️
Our newest small open model is built for local assistants, interactive characters and robots that can carry on a conversation and use tools to get things done.
Watch Reachy Mini chat and move, with Bolt handling conversation and NVIDIA Cosmos handling vision. Both models run locally on Jetson Orin Nano 8GB.
Learn more: research.nvidia.com/labs/nem…
DeepLearning.Hub retweeted
Introducing Carbon-X: The best open DNA model.
We midtrained a 14B model on DNA and text, and it beats every open language model and matches GPT-6.1 Sol at 1,000x lower cost.
Ask it about a sequence, what a mutation does, or to generate new DNA.
huggingface.co/HuggingFaceBi…
DeepLearning.Hub retweeted
Run Flint locally on 24GB RAM via Unsloth Dynamic GGUFs!
Flint is the strongest MoE model under 50B parameters.
Recursive’s Apache-2.0 model has 39.8B parameters (2.5B active). Run at 125 t/s on Mac, 150 on RTX Spark
GGUF: huggingface.co/unsloth/flint…
Guide: unsloth.ai/docs/models/flint
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 scratch in under 4 months
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.
DeepLearning.Hub retweeted
DeepSeek V4.1-Flash-1017 can now run locally! 🐳
We made 1-bit retain ~88.2% accuracy while shrinking size from 508GB to 250GB (−52%).
Run on a 128GB+ RAM device.
V4.1 Flash 1017 is the strongest open model to date
Guide: unsloth.ai/docs/models/deeps…
GGUF: huggingface.co/unsloth/DeepS…
🚀 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, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
DeepLearning.Hub retweeted
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/DeepI…
1/4
DeepLearning.Hub retweeted
Beam is a token-efficient, frontier-scale model for your coding agents, comes with its own harness 🔥
A23B/501B model, also comes with NVFP4 & FP8 and day-0 transformers support 🤗
check out our blog ⤵️
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 harness we built and trained Beam on: Mirror CLI
Weights and model card on Hugging Face: huggingface.co/reflection


































