unsloth/Kimi-K3-GGUF
Image-Text-to-Text • 2.8T • Updated • 170k • 299
🏗️ Building on HF
almer
almernzh
AI & ML interests
None yet
Recent Activity
liked a model 7 days ago
unsloth/Kimi-K3-GGUF liked a model 8 days ago
moonshotai/Kimi-K3 liked a model 11 days ago
poolside/Laguna-S-2.1Organizations
liked a
model 7 days ago
liked a
model 8 days ago
liked a
model 11 days ago
reacted to SeaWolf-AI's post with 👍 12 days ago
Post
4034
📱 POCKET — a 35-billion-parameter model that runs on your iPhone, and on your PC with no GPU
We're releasing POCKET, VIDRAFT's flagship Darwin-36B-Opus compressed for on-device use. No fork, no CUDA, no cloud — it runs on stock llama.cpp. It's a sparse Mixture-of-Experts model (256 experts, only 8 active per token), so the file can be large while the work per token stays small. That's what lets a 35B model run on a phone, and generate fast on a CPU with no graphics card.
Measured (POCKET-35B IQ1_M vs Bonsai-27B Q1_0):
• CPU generate (Xeon, 16 threads): 27.0 vs 10.1 tok/s → 2.69× faster
• GPU generate (H100): 197 vs 89 tok/s → 2.22× faster
• GPU prompt processing (H100): 753 vs 1816 → 0.41× (Bonsai wins this one — MoE prefill wakes every expert, so sparsity stops helping there. We say so.)
• Quality (HellaSwag, 400 q): 61.0% vs 60.0% → a tie (confidence intervals overlap)
On a real consumer laptop — MacBook M3 Pro (18 GB) — POCKET wins every axis, prompt processing included:
• Metal generate: 25.4 vs 12.8 → 1.99×
• CPU generate: 13.8 vs 4.4 → 3.13×
• Metal prompt: 240.7 vs 73.4 → 3.28×
One more quiet fact: the same-size, quality-oriented rival Ternary-Bonsai-27B (7.2 GB) fails to load in upstream llama.cpp at all — it needs the PrismML fork. POCKET runs on the tools you already have: LM Studio, Ollama, PocketPal, MLX.
📖 Full story (tech, measurements, recipes): https://huggingface.co/blog/FINAL-Bench/pocket
Models:
📦 POCKET-35B-GGUF (PC / server, no GPU): FINAL-Bench/POCKET-35B-GGUF
🇰🇷 POCKET-KR-GGUF (Android): FINAL-Bench/POCKET-KR-GGUF
🍎 POCKET-KR-MLX (iPhone / Mac): FINAL-Bench/POCKET-KR-MLX
🌍 POCKET-EN-GGUF (English phone / PC): FINAL-Bench/POCKET-EN-GGUF
🖥️ Live demo (answering on a CPU, no GPU): FINAL-Bench/POCKET-35B-CPU
📚 Collection: FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6
We're releasing POCKET, VIDRAFT's flagship Darwin-36B-Opus compressed for on-device use. No fork, no CUDA, no cloud — it runs on stock llama.cpp. It's a sparse Mixture-of-Experts model (256 experts, only 8 active per token), so the file can be large while the work per token stays small. That's what lets a 35B model run on a phone, and generate fast on a CPU with no graphics card.
Measured (POCKET-35B IQ1_M vs Bonsai-27B Q1_0):
• CPU generate (Xeon, 16 threads): 27.0 vs 10.1 tok/s → 2.69× faster
• GPU generate (H100): 197 vs 89 tok/s → 2.22× faster
• GPU prompt processing (H100): 753 vs 1816 → 0.41× (Bonsai wins this one — MoE prefill wakes every expert, so sparsity stops helping there. We say so.)
• Quality (HellaSwag, 400 q): 61.0% vs 60.0% → a tie (confidence intervals overlap)
On a real consumer laptop — MacBook M3 Pro (18 GB) — POCKET wins every axis, prompt processing included:
• Metal generate: 25.4 vs 12.8 → 1.99×
• CPU generate: 13.8 vs 4.4 → 3.13×
• Metal prompt: 240.7 vs 73.4 → 3.28×
One more quiet fact: the same-size, quality-oriented rival Ternary-Bonsai-27B (7.2 GB) fails to load in upstream llama.cpp at all — it needs the PrismML fork. POCKET runs on the tools you already have: LM Studio, Ollama, PocketPal, MLX.
📖 Full story (tech, measurements, recipes): https://huggingface.co/blog/FINAL-Bench/pocket
Models:
📦 POCKET-35B-GGUF (PC / server, no GPU): FINAL-Bench/POCKET-35B-GGUF
🇰🇷 POCKET-KR-GGUF (Android): FINAL-Bench/POCKET-KR-GGUF
🍎 POCKET-KR-MLX (iPhone / Mac): FINAL-Bench/POCKET-KR-MLX
🌍 POCKET-EN-GGUF (English phone / PC): FINAL-Bench/POCKET-EN-GGUF
🖥️ Live demo (answering on a CPU, no GPU): FINAL-Bench/POCKET-35B-CPU
📚 Collection: FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6
- 5 replies
reacted to ovi054's post with ❤️ about 1 month ago
Post
4461
Turn any topic to animation explainer video
It is powered by Qwen3-14B + Manim LoRA and turns any concept into a Manim explainer video.
👉 Try it now:
build-small-hackathon/anim-vid-ai
It is powered by Qwen3-14B + Manim LoRA and turns any concept into a Manim explainer video.
👉 Try it now:
build-small-hackathon/anim-vid-ai
liked a
Space about 1 month ago
reacted to projectlosangeles's post with 🔥 about 1 month ago
Post
6597
🔥If you love multi-modal art🎨, please check out "A Million Little Fibers" project!!!🔥
https://github.com/asigalov61/A-Million-Little-Fibers-2026
https://soundcloud.com/aleksandr-sigalov-61/sets/a-million-little-fibers
This brand new 2026 edition covers three SOTA models:
zai-org/GLM-5.2
k2-fsa/OmniVoice
HeartMuLa/HeartMuLa-oss-3B-happy-new-year
The project aims to showcase what kind of multi-modal art is now possible to create with these amazing OSS resources!
If you enjoyed the project, please ⭐or 🔱 GitHub repo and❤️on SoundCloud and Hugging Face. It really helps!
Most sincerely,
Alex
Project Los Angeles
Tegridy Code 2026
P.S. Don't forget to bring a towel! 😂
@multimodalart
@victor
@John6666
https://github.com/asigalov61/A-Million-Little-Fibers-2026
https://soundcloud.com/aleksandr-sigalov-61/sets/a-million-little-fibers
This brand new 2026 edition covers three SOTA models:
zai-org/GLM-5.2
k2-fsa/OmniVoice
HeartMuLa/HeartMuLa-oss-3B-happy-new-year
The project aims to showcase what kind of multi-modal art is now possible to create with these amazing OSS resources!
If you enjoyed the project, please ⭐or 🔱 GitHub repo and❤️on SoundCloud and Hugging Face. It really helps!
Most sincerely,
Alex
Project Los Angeles
Tegridy Code 2026
P.S. Don't forget to bring a towel! 😂
@multimodalart
@victor
@John6666
- 3 replies
updated a
model about 1 month ago
published a
model about 1 month ago
liked a
model about 1 month ago
reacted to ST-x-Tony's post with ❤️ about 1 month ago
Post
7166
Hello AI Community! 👋
We are thrilled to announce the release of **NRS_QWEN_MYTHOS_1M**, a high-performance reasoning model built on the powerful **Qwen 3.5 9B** base. At **SKT AI LABS**, we’ve applied our proprietary **Neural Reasoning System (NRS)** to push the boundaries of what a 9B model can do.
🔥 **Why this model is a Game-Changer:**
✅ **100x High Reasoning Capacity:** Deep logical thinking and complex problem-solving via NRS Boosting.
✅ **1 Million Token Context:** Handle massive codebases, long documents, and multi-turn agentic tasks with ease (YaRN Scaling).
✅ **Advanced Thinking Mode:** Native
✅ **Tool-Use Ready:** Optimized for Python execution and Web Search with self-correction.
✅ **Blazing Fast:** Efficient 9B architecture that runs smoothly on consumer hardware (RTX 3090/4090).
🛠️ **Technical Highlights:**
* **Base:** Qwen 3.5 9B
* **Tuning:** NRS Specific Tuning high-quality samples.
* **License:** NRS DOCS
Whether you are a developer building coding agents, a researcher dealing with long-context data, or just someone who loves deep reasoning, this model is built for you.
👇 **Try it now on Hugging Face:**
SKT-NRS/NRS_QWEN_MYTHOS_1M
We are thrilled to announce the release of **NRS_QWEN_MYTHOS_1M**, a high-performance reasoning model built on the powerful **Qwen 3.5 9B** base. At **SKT AI LABS**, we’ve applied our proprietary **Neural Reasoning System (NRS)** to push the boundaries of what a 9B model can do.
🔥 **Why this model is a Game-Changer:**
✅ **100x High Reasoning Capacity:** Deep logical thinking and complex problem-solving via NRS Boosting.
✅ **1 Million Token Context:** Handle massive codebases, long documents, and multi-turn agentic tasks with ease (YaRN Scaling).
✅ **Advanced Thinking Mode:** Native
<think> tags for step-by-step Chain-of-Thought reasoning.✅ **Tool-Use Ready:** Optimized for Python execution and Web Search with self-correction.
✅ **Blazing Fast:** Efficient 9B architecture that runs smoothly on consumer hardware (RTX 3090/4090).
🛠️ **Technical Highlights:**
* **Base:** Qwen 3.5 9B
* **Tuning:** NRS Specific Tuning high-quality samples.
* **License:** NRS DOCS
Whether you are a developer building coding agents, a researcher dealing with long-context data, or just someone who loves deep reasoning, this model is built for you.
👇 **Try it now on Hugging Face:**
SKT-NRS/NRS_QWEN_MYTHOS_1M
- 1 reply
liked a
Space about 1 month ago
updated a
model about 1 month ago
published a
model about 1 month ago
liked 4
models about 1 month ago
baidu/Unlimited-OCR
Image-Text-to-Text • 3B • Updated • 2.7M • 3.87k
andrevp/Ornith-1.0-9B-Heretic-Uncensored
Image-Text-to-Text • 9B • Updated • 1.69k • • 10
nvidia/GLM-5.2-NVFP4
Text Generation • 381B • Updated • 1.8M • 305
deepreinforce-ai/Ornith-1.0-35B
Text Generation • 665k • Updated • 2.83M • 467
upvoted a collection about 1 month ago
reacted to ST-x-Tony's post with ❤️ about 1 month ago
Post
10456
Hello everyone,
We are excited to share that SKT-NRS is now live on Hugging Face.
We’ve developed a Neural Reasoning System (NRS) designed to enhance the capabilities of foundation models — giving them stronger reasoning, improved performance, and more reliable outputs across a wide range of tasks.
Our goal is to bring meaningful quality improvements to both new and existing models. You’ll start seeing boosted versions of various models released here soon, each refined with our NRS approach.
**What to Expect* ❤️🩹
Regular releases of Neural Reasoning-enhanced models
Clear focus on better reasoning and overall model quality
Ongoing improvements based on community feedback
If you’d like to stay updated, feel free to follow this space — we’ll be posting the first boosted models very soon.
**Community Requests**
Have a specific model you’d like us to work on? Looking for improvements on an existing model, or have any other requests?
We’re happy to hear from you. Please share your suggestions here:
## Community Requests → SKT-NRS/README#1
**Thank you for your support! We look forward to building better models together.**
We are excited to share that SKT-NRS is now live on Hugging Face.
We’ve developed a Neural Reasoning System (NRS) designed to enhance the capabilities of foundation models — giving them stronger reasoning, improved performance, and more reliable outputs across a wide range of tasks.
Our goal is to bring meaningful quality improvements to both new and existing models. You’ll start seeing boosted versions of various models released here soon, each refined with our NRS approach.
**What to Expect* ❤️🩹
Regular releases of Neural Reasoning-enhanced models
Clear focus on better reasoning and overall model quality
Ongoing improvements based on community feedback
If you’d like to stay updated, feel free to follow this space — we’ll be posting the first boosted models very soon.
**Community Requests**
Have a specific model you’d like us to work on? Looking for improvements on an existing model, or have any other requests?
We’re happy to hear from you. Please share your suggestions here:
## Community Requests → SKT-NRS/README#1
**Thank you for your support! We look forward to building better models together.**
- 10 replies