Granite 4.0 Nano: Just how small can you go?
•
121
AI & ML interests
LLMs for language and code + Time series and geospatial foundation models
Recent Activity
View all activity
Papers
View all Papers
Articles
danielhanchen
posted
an
update
3 days ago
Post
384
Run Qwen-Image-2512, the new SOTA text-to-image model! 💜
It's the top performing open diffusion model and has more realistic + accurate images/text.
Run locally with 14GB RAM via our Dynamic GGUF: unsloth/Qwen-Image-2512-GGUF
Guide: https://unsloth.ai/docs/models/qwen-image-2512
It's the top performing open diffusion model and has more realistic + accurate images/text.
Run locally with 14GB RAM via our Dynamic GGUF: unsloth/Qwen-Image-2512-GGUF
Guide: https://unsloth.ai/docs/models/qwen-image-2512
- 1 reply
danielhanchen
posted
an
update
11 days ago
Post
3769
You can now run GLM-4.7, the new 355B parameter SOTA model on your local device (128GB RAM).✨
The model achieves SOTA performance on coding, agentic and chat benchmarks.
GGUF: unsloth/GLM-4.7-GGUF
Guide: https://docs.unsloth.ai/models/glm-4.7
The model achieves SOTA performance on coding, agentic and chat benchmarks.
GGUF: unsloth/GLM-4.7-GGUF
Guide: https://docs.unsloth.ai/models/glm-4.7
- 3 replies
ibibrahim
published
a
model
12 days ago
Add Granite 3.3 8b LoRAs
#3 opened 15 days ago
by
frreiss
danielhanchen
posted
an
update
16 days ago
Post
2266
Google releases FunctionGemma, a new 270M parameter model that runs on just 0.5 GB RAM.✨
Built for tool-calling, run locally on your phone at 50+ tokens/s, or fine-tune with Unsloth & deploy to your phone.
GGUF: unsloth/functiongemma-270m-it-GGUF
Docs + Notebook: https://docs.unsloth.ai/models/functiongemma
Built for tool-calling, run locally on your phone at 50+ tokens/s, or fine-tune with Unsloth & deploy to your phone.
GGUF: unsloth/functiongemma-270m-it-GGUF
Docs + Notebook: https://docs.unsloth.ai/models/functiongemma
-
- 2 replies
F16 broken
2
#1 opened 17 days ago
by
ramendik
gabegoodhart
updated
a
model
16 days ago
Flash Attention v2 doesnt work
1
#20 opened 24 days ago
by
abcdefghijklmnop52
frreiss
updated
a
model
18 days ago
danielhanchen
posted
an
update
19 days ago
Post
5307
NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model! 🔥
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
💚 Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
💚 Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
- 1 reply
frreiss
published
a
model
23 days ago
danielhanchen
posted
an
update
23 days ago
Post
2038
Mistral's new SOTA coding models Devstral 2 can now be Run locally! (25GB RAM) 🐱
We fixed the chat template, so performance should be much better now!
24B: unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF
123B: unsloth/Devstral-2-123B-Instruct-2512-GGUF
🧡Step-by-step Guide: https://docs.unsloth.ai/models/devstral-2
We fixed the chat template, so performance should be much better now!
24B: unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF
123B: unsloth/Devstral-2-123B-Instruct-2512-GGUF
🧡Step-by-step Guide: https://docs.unsloth.ai/models/devstral-2
alozowski
authored
a
paper
25 days ago
Add run Ollama script
2
#32 opened 26 days ago
by
kndtran
Import files
#1 opened 26 days ago
by
frreiss
Create .gitattributes
#3 opened 26 days ago
by
javiccano
Create .gitattributes
#3 opened 26 days ago
by
javiccano
Upload 9 files
#2 opened 27 days ago
by
javiccano
Update README.md
#1 opened about 1 month ago
by
javiccano
Upload 9 files
#2 opened 27 days ago
by
javiccano