Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
Paper • 2605.27295 • Published • 23
AI & ML interests
Unofficial org for community upload of Mistral's Open Source models.
Recent Activity
View all activity
nielsr
submitted a
paper to Daily Papers 6 days ago
nielsr
submitted a
paper to Daily Papers 12 days ago
danielhanchen
posted an update 13 days ago
Post
2607
Qwen3.6 MTP is here! Run locally on 20GB RAM. ⚡️
MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.
Qwen3.6-27B: unsloth/Qwen3.6-27B-MTP-GGUF
Qwen3.6-35B-A3B: unsloth/Qwen3.6-35B-A3B-MTP-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6#mtp-guide
MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.
Qwen3.6-27B: unsloth/Qwen3.6-27B-MTP-GGUF
Qwen3.6-35B-A3B: unsloth/Qwen3.6-35B-A3B-MTP-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6#mtp-guide
- 2 replies
danielhanchen
posted an update 20 days ago
Post
5794
We’re excited to announce that Unsloth has joined the PyTorch Ecosystem! 🔥🦥
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! 💕
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! 💕
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
- 2 replies
danielhanchen
posted an update 24 days ago
Post
7691
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
danielhanchen
posted an update 28 days ago
Post
8839
We made a guide on how to run open LLMs in Claude Code, Codex and OpenClaw.
Use Gemma 4 and Qwen3.6 GGUFs for local agentic coding on 24GB RAM
Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp
Guide: https://unsloth.ai/docs/basics/api
Use Gemma 4 and Qwen3.6 GGUFs for local agentic coding on 24GB RAM
Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp
Guide: https://unsloth.ai/docs/basics/api
danielhanchen
posted an update about 1 month ago
nielsr
submitted a
paper to Daily Papers about 1 month ago
danielhanchen
posted an update about 1 month ago
Post
5356
Qwen3.6-27B is out now! Run it locally on 18GB RAM. 💜
Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.
GGUFs to run: unsloth/Qwen3.6-27B-GGUF
Guide + MLX: https://unsloth.ai/docs/models/qwen3.6
Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.
GGUFs to run: unsloth/Qwen3.6-27B-GGUF
Guide + MLX: https://unsloth.ai/docs/models/qwen3.6
danielhanchen
posted an update about 2 months ago
Post
2849
Qwen3.6-35B-A3B can now be run locally! 💜
The model is the strongest mid-sized LLM on nearly all benchmarks.
Run on 23GB RAM via Unsloth Dynamic GGUFs.
GGUFs to run: unsloth/Qwen3.6-35B-A3B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6
The model is the strongest mid-sized LLM on nearly all benchmarks.
Run on 23GB RAM via Unsloth Dynamic GGUFs.
GGUFs to run: unsloth/Qwen3.6-35B-A3B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6
- 13 replies
nielsr
submitted 2
papers to Daily Papers about 2 months ago
danielhanchen
posted an update about 2 months ago
Post
5511
You can now fine-tune Gemma 4 for free with our notebooks! 🔥
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
- 5 replies
nielsr
submitted a
paper to Daily Papers 2 months ago
danielhanchen
posted an update 2 months ago
Post
3846
Google releases Gemma 4. ✨
Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B.
The multimodal reasoning models are under Apache 2.0.
Run E2B and E4B on ~6GB RAM, and on phones. Run 26B-A4B and 31B on ~18GB.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4
Guide: https://unsloth.ai/docs/models/gemma-4
Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B.
The multimodal reasoning models are under Apache 2.0.
Run E2B and E4B on ~6GB RAM, and on phones. Run 26B-A4B and 31B on ~18GB.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4
Guide: https://unsloth.ai/docs/models/gemma-4
danielhanchen
posted an update 2 months ago
Post
2795
A new way to use Unsloth.
Coming soon...
Coming soon...
MaziyarPanahi
posted an update 2 months ago
Post
3139
Training mRNA Language Models Across 25 Species for $165
We built an end-to-end protein AI pipeline covering structure prediction, sequence design, and codon optimization. After comparing multiple transformer architectures for codon-level language modeling, CodonRoBERTa-large-v2 emerged as the clear winner with a perplexity of 4.10 and a Spearman CAI correlation of 0.40, significantly outperforming ModernBERT. We then scaled to 25 species, trained 4 production models in 55 GPU-hours, and built a species-conditioned system that no other open-source project offers. Complete results, architectural decisions, and runnable code below.
https://huggingface.co/blog/OpenMed/training-mrna-models-25-species
We built an end-to-end protein AI pipeline covering structure prediction, sequence design, and codon optimization. After comparing multiple transformer architectures for codon-level language modeling, CodonRoBERTa-large-v2 emerged as the clear winner with a perplexity of 4.10 and a Spearman CAI correlation of 0.40, significantly outperforming ModernBERT. We then scaled to 25 species, trained 4 production models in 55 GPU-hours, and built a species-conditioned system that no other open-source project offers. Complete results, architectural decisions, and runnable code below.
https://huggingface.co/blog/OpenMed/training-mrna-models-25-species
danielhanchen
posted an update 2 months ago
Post
944
You don’t need to set LLM parameters anymore! 🚀
llama.cpp uses only the context length + compute your local setup needs. Unsloth also auto-applies the correct model settings
Try in Unsloth Studio - now with precompiled llama.cpp binaries.
GitHub: https://github.com/unslothai/unsloth
llama.cpp uses only the context length + compute your local setup needs. Unsloth also auto-applies the correct model settings
Try in Unsloth Studio - now with precompiled llama.cpp binaries.
GitHub: https://github.com/unslothai/unsloth
- 2 replies
MaziyarPanahi
posted an update 2 months ago
Post
2330
We annotated 119K medical images with two frontier VLMs (Qwen 3.5, Kimi K2.5), cross-validated at 93% agreement, and produced 110K training records, all for under $500. Fine-tuning 3 small models (2-3B params) improved all benchmarks: best model reaches +15.0% average exact match.
Everything is open-sourced: datasets, adapters, and code.
https://huggingface.co/blog/OpenMed/synthvision
Everything is open-sourced: datasets, adapters, and code.
https://huggingface.co/blog/OpenMed/synthvision
- 2 replies
nielsr
submitted a
paper to Daily Papers 2 months ago