Qwen3-TTS Technical Report
Paper
β’
2601.15621
β’
Published
β’
36
AI & ML interests
Unofficial org for community upload of Mistral's Open Source models.
Recent Activity
View all activity
JustinLin610Β
authored
a
paper
3 days ago
danielhanchenΒ
posted
an
update
4 days ago
Post
2393
You can now fine-tune embedding models in our free Unsloth notebook! π€
Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data.
β Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning
Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups.
We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!
Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data.
β Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning
Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups.
We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!
- 1 reply
danielhanchenΒ
posted
an
update
6 days ago
Post
2504
Run GLM-4.7-Flash locally on your device with 24GB RAM!π₯
It's the best performing 30B model on SWE-Bench and GPQA. With 200K context, it excels at coding, agents, chat & reasoning.
GGUF: unsloth/GLM-4.7-Flash-GGUF
Guide: https://unsloth.ai/docs/models/glm-4.7-flash
It's the best performing 30B model on SWE-Bench and GPQA. With 200K context, it excels at coding, agents, chat & reasoning.
GGUF: unsloth/GLM-4.7-Flash-GGUF
Guide: https://unsloth.ai/docs/models/glm-4.7-flash
danielhanchenΒ
posted
an
update
11 days ago
Post
2759
You can now do reinforcement learning training with 7Γ longer context and no accuracy loss, via our new batching algorithms.
Long reasoning chains in RL are costly, but now we enable you to train gpt-oss with GRPO & reach 380K context on a 192GB GPU.
Blog: https://unsloth.ai/docs/new/grpo-long-context
Long reasoning chains in RL are costly, but now we enable you to train gpt-oss with GRPO & reach 380K context on a 192GB GPU.
Blog: https://unsloth.ai/docs/new/grpo-long-context
nielsrΒ
submitted
a
paper
to Daily Papers
14 days ago
MaziyarPanahiΒ
posted
an
update
20 days ago
Post
3139
π OpenMed 2025 Year in Review: 6 Months of Open Medical AI
I'm thrilled to share what the OpenMed community has accomplished since our July 2025 launch!
π The Numbers
29,700,000 downloads Thank you! π
- 481 total models (475 medical NER models + 6 fine-tuned LLMs)
- 475 medical NER models in [OpenMed](
OpenMed
) organization
- 6 fine-tuned LLMs in [openmed-community](
openmed-community
)
- 551,800 PyPI downloads of the [openmed package](https://pypi.org/project/openmed/)
- 707 followers on HuggingFace (you!)
- 97 GitHub stars on the [toolkit repo](https://github.com/maziyarpanahi/openmed)
π Top Models by Downloads
1. [OpenMed-NER-PharmaDetect-SuperClinical-434M]( OpenMed/OpenMed-NER-PharmaDetect-SuperClinical-434M) β 147,305 downloads
2. [OpenMed-NER-ChemicalDetect-ElectraMed-33M]( OpenMed/OpenMed-NER-ChemicalDetect-ElectraMed-33M) β 126,785 downloads
3. [OpenMed-NER-BloodCancerDetect-TinyMed-65M]( OpenMed/OpenMed-NER-BloodCancerDetect-TinyMed-65M) β 126,465 downloads
π¬ Model Categories
Our 481 models cover comprehensive medical domains:
- Disease Detection (~50 variants)
- Pharmaceutical Detection (~50 variants)
- Oncology Detection (~50 variants)
- Genomics/DNA Detection (~80 variants)
- Chemical Detection (~50 variants)
- Species/Organism Detection (~60 variants)
- Protein Detection (~50 variants)
- Pathology Detection (~50 variants)
- Blood Cancer Detection (~30 variants)
- Anatomy Detection (~40 variants)
- Zero-Shot NER (GLiNER-based)
OpenMed
OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets (2508.01630)
https://huggingface.co/collections/OpenMed/medical-and-clinical-ner
https://huggingface.co/collections/OpenMed/zeroshot-medical-and-clinical-ner
OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B
I'm thrilled to share what the OpenMed community has accomplished since our July 2025 launch!
π The Numbers
29,700,000 downloads Thank you! π
- 481 total models (475 medical NER models + 6 fine-tuned LLMs)
- 475 medical NER models in [OpenMed](
- 6 fine-tuned LLMs in [openmed-community](
- 551,800 PyPI downloads of the [openmed package](https://pypi.org/project/openmed/)
- 707 followers on HuggingFace (you!)
- 97 GitHub stars on the [toolkit repo](https://github.com/maziyarpanahi/openmed)
π Top Models by Downloads
1. [OpenMed-NER-PharmaDetect-SuperClinical-434M]( OpenMed/OpenMed-NER-PharmaDetect-SuperClinical-434M) β 147,305 downloads
2. [OpenMed-NER-ChemicalDetect-ElectraMed-33M]( OpenMed/OpenMed-NER-ChemicalDetect-ElectraMed-33M) β 126,785 downloads
3. [OpenMed-NER-BloodCancerDetect-TinyMed-65M]( OpenMed/OpenMed-NER-BloodCancerDetect-TinyMed-65M) β 126,465 downloads
π¬ Model Categories
Our 481 models cover comprehensive medical domains:
- Disease Detection (~50 variants)
- Pharmaceutical Detection (~50 variants)
- Oncology Detection (~50 variants)
- Genomics/DNA Detection (~80 variants)
- Chemical Detection (~50 variants)
- Species/Organism Detection (~60 variants)
- Protein Detection (~50 variants)
- Pathology Detection (~50 variants)
- Blood Cancer Detection (~30 variants)
- Anatomy Detection (~40 variants)
- Zero-Shot NER (GLiNER-based)
OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets (2508.01630)
https://huggingface.co/collections/OpenMed/medical-and-clinical-ner
https://huggingface.co/collections/OpenMed/zeroshot-medical-and-clinical-ner
OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B
-
- 1 reply
danielhanchenΒ
posted
an
update
26 days ago
Post
920
Run Qwen-Image-2512, the new SOTA text-to-image model! π
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
- 2 replies
nielsrΒ
submitted
a
paper
to Daily Papers
about 1 month ago
danielhanchenΒ
posted
an
update
about 1 month ago
Post
4062
You can now run GLM-4.7, the new 355B parameter SOTA model on your local device (128GB RAM).β¨
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
danielhanchenΒ
posted
an
update
about 1 month ago
Post
2463
Google releases FunctionGemma, a new 270M parameter model that runs on just 0.5 GB RAM.β¨
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
danielhanchenΒ
posted
an
update
about 1 month ago
Post
5506
NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model! π₯
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
π 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
π Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
- 1 reply
danielhanchenΒ
posted
an
update
about 2 months ago
Post
2170
Mistral's new SOTA coding models Devstral 2 can now be Run locally! (25GB RAM) π±
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
π§‘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
π§‘Step-by-step Guide: https://docs.unsloth.ai/models/devstral-2
mrfakenameΒ
posted
an
update
about 2 months ago
Post
10603
Excited to share that I've joined the Hugging Face Fellows program! π€
Looking forward to contributing to & working more closely with the open-source ecosystem - huge thanks to everyone who's supported me on this journey! π
Looking forward to contributing to & working more closely with the open-source ecosystem - huge thanks to everyone who's supported me on this journey! π
danielhanchenΒ
posted
an
update
about 2 months ago
Post
3839
Mistral's new Ministral 3 models can now be Run & Fine-tuned locally! (16GB RAM)
Ministral 3 have vision support and the best-in-class performance for their sizes.
14B Instruct GGUF: unsloth/Ministral-3-14B-Instruct-2512-GGUF
14B Reasoning GGUF: unsloth/Ministral-3-14B-Reasoning-2512-GGUF
π± Step-by-step Guide: https://docs.unsloth.ai/new/ministral-3
All GGUFs, BnB, FP8 etc. variants uploads: https://huggingface.co/collections/unsloth/ministral-3
Ministral 3 have vision support and the best-in-class performance for their sizes.
14B Instruct GGUF: unsloth/Ministral-3-14B-Instruct-2512-GGUF
14B Reasoning GGUF: unsloth/Ministral-3-14B-Reasoning-2512-GGUF
π± Step-by-step Guide: https://docs.unsloth.ai/new/ministral-3
All GGUFs, BnB, FP8 etc. variants uploads: https://huggingface.co/collections/unsloth/ministral-3
-
- 3 replies
danielhanchenΒ
posted
an
update
about 2 months ago
Post
8568
Qwen3-Next can now be Run locally! (30GB RAM)
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
π Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
π Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
reach-vbΒ
authored
a
paper
2 months ago
danielhanchenΒ
posted
an
update
3 months ago
Post
4445
You can now run Kimi K2 Thinking locally with our Dynamic 1-bit GGUFs:
unsloth/Kimi-K2-Thinking-GGUF
We shrank the 1T model to 245GB (-62%) & retained ~85% of accuracy on Aider Polyglot. Run on >247GB RAM for fast inference.
We also collaborated with the Moonshot AI Kimi team on a system prompt fix! π₯°
Guide + fix details: https://docs.unsloth.ai/models/kimi-k2-thinking-how-to-run-locally
We shrank the 1T model to 245GB (-62%) & retained ~85% of accuracy on Aider Polyglot. Run on >247GB RAM for fast inference.
We also collaborated with the Moonshot AI Kimi team on a system prompt fix! π₯°
Guide + fix details: https://docs.unsloth.ai/models/kimi-k2-thinking-how-to-run-locally
mrfakenameΒ
posted
an
update
3 months ago
Post
6188
Trained a model for emotion-controllable TTS based on MiMo audio on LAION's dataset.
Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.
Will probably kick off a new run later with some settings tweaked.
Put up a demo here: https://huggingface.co/spaces/mrfakename/EmoAct-MiMo
(Turn π on to hear audio samples)
Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.
Will probably kick off a new run later with some settings tweaked.
Put up a demo here: https://huggingface.co/spaces/mrfakename/EmoAct-MiMo
(Turn π on to hear audio samples)
-
- 5 replies
JustinLin610Β
authored
a
paper
4 months ago
danielhanchenΒ
posted
an
update
5 months ago
Post
6634
Run DeepSeek-V3.1 locally on 170GB RAM with Dynamic 1-bit GGUFs!π
GGUFs: unsloth/DeepSeek-V3.1-GGUF
The 715GB model gets reduced to 170GB (-80% size) by smartly quantizing layers.
The 1-bit GGUF passes all our code tests & we fixed the chat template for llama.cpp supported backends.
Guide: https://docs.unsloth.ai/basics/deepseek-v3.1
GGUFs: unsloth/DeepSeek-V3.1-GGUF
The 715GB model gets reduced to 170GB (-80% size) by smartly quantizing layers.
The 1-bit GGUF passes all our code tests & we fixed the chat template for llama.cpp supported backends.
Guide: https://docs.unsloth.ai/basics/deepseek-v3.1