Recursive Superintelligence, Inc.

Team

company

https://recursive.com/

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

jtobin-recursive new activity 20 days ago

RecursiveSI/flint:Why SI and not AI?

alexey-recursive published a model 20 days ago

RecursiveSI/flint-nvfp4-gguf

alexey-recursive published a model 20 days ago

RecursiveSI/flint-int4-gguf

View all activity

Team members 30
private

danielhanchen

posted an update 2 days ago

Post

5,395

Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use.

Unsloth Dynamic V3.1 GGUFs bring thinking & token use to match 95% of full precision Qwen3.8-Flash.

Results: 50% fewer tokens + 15% higher accuracy vs same size quants.

GGUF: unsloth/Qwen3.8-Flash-Next-GGUF
Analysis/Guide: https://unsloth.ai/docs/models/qwen3.8-next

3 replies

danielhanchen

posted an update 6 days ago

Post

7,249

We’re releasing new Qwen3.8-Flash-Next GGUFs with 15% higher accuracy.

Unsloth Dynamic V3.1 outperforms others by >15% on Terminal Bench, DeepSWE & more benchmarks (256K context).

Run on 32GB+ RAM setups.

GGUF: unsloth/Qwen3.8-Flash-Next-GGUF
Blog: https://unsloth.ai/docs/models/qwen3.8-next

shimmyshimmer

posted an update 6 days ago

Post

716

We benchmarked DeepSeek-V4.1-Flash-1017 GGUFs on Terminal Bench, DeepSWE & more on 512K context. Unsloth ranks #1 overall.

1-bit Unsloth GGUF scores 68.1 on DeepSWE, 72.2 on Terminal-Bench, 52.7 on AutomationBench. >10% ahead of other quants.

GGUF: unsloth/DeepSeek-V4.1-Flash-1017-GGUF

danielhanchen

posted an update 11 days ago

Post

815

We’re releasing new DeepSeek-V4.1-Flash-1017 GGUFs, ranking highest across benchmarks. 🐋

Dynamic V3.1 leads across nearly all benchmarks: GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, Aider & more.

Run on 64GB+ RAM.

GGUF: unsloth/DeepSeek-V4.1-Flash-1017-GGUF
Blog: https://unsloth.ai/docs/models/deepseek-v4.1-flash

1 reply

danielhanchen

posted an update 12 days ago

Post

2,518

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: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/browser-use

1 reply

jtobin-recursive

in RecursiveSI/flint 20 days ago

Why SI and not AI?

➕ 23

#1 opened 20 days ago by

PotatoSniffer

alexey-recursive

published 3 models 20 days ago

published a model 20 days ago

RecursiveSI/flint

Text Generation • 40B • Updated 20 days ago • 47.8k • 1.39k

alexey-recursive

updated 3 models 20 days ago

RecursiveSI/flint-int4-gguf

Text Generation • 40B • Updated 20 days ago • 53.5k • 35

RecursiveSI/flint-nvfp4-gguf

Text Generation • 40B • Updated 20 days ago • 130k • 40

RecursiveSI/flint-int4

Text Generation • Updated 20 days ago • 18.7k • 31

lvmopt

updated a model 20 days ago

RecursiveSI/flint

Text Generation • 40B • Updated 20 days ago • 47.8k • 1.39k

danielhanchen

posted an update 22 days ago

Post

5,068

Run DeepSeek V4.1-Flash-1017 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: https://unsloth.ai/docs/models/deepseek-v4.1-flash
GGUF: unsloth/DeepSeek-V4.1-Flash-1017-GGUF

danielhanchen

posted an update about 1 month ago

Post

5,183

You can now train your own Decision model like Jev locally!

We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.

Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.

GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth

5 replies

danielhanchen

posted an update about 1 month ago

Post

4,157

Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.

The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).

Run & train the model via Unsloth.

GGUF: unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2

danielhanchen

posted an update about 2 months ago

Post

9,207

Unsloth has surpassed 500M model downloads on Hugging Face! 🦥🤗

Qwen3.8-27B GGUF is already Unsloth’s #1 most-downloaded model ever.

Thanks for all your support! Follow us:

unsloth

1 reply

danielhanchen

posted an update about 2 months ago

Post

3,778

Qwen-Image-2.1 can now run locally on 12GB VRAM with Unsloth GGUFs! 🖼️

The 7B model performs on par with Nano Banana 2.0.

For higher quality, you can also run Dynamic FP8 on just 6GB of VRAM via offloading.

GGUF: unsloth/Qwen-Image-2.1-GGUF
Guide: https://unsloth.ai/docs/models/qwen-image-2.1

danielhanchen

posted an update 2 months ago

Post

6,941

Qwen3.8-27B Unsloth GGUF is now the #1 most-liked GGUF of all time! 🤗🦥

The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you.

GGUF: unsloth/Qwen3.8-27B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.8

5 replies

AI & ML interests

Recent Activity

Team members 30 private

RecursiveSI's activity

Why SI and not AI?

Team members 30
private