allura-forge/Llama-3.3-8B-Instruct
8B
•
Updated
•
1.83k
•
162
Tyler
unmodeled-tyler
AI & ML interests
AI research engineer. The human behind VANTA Research.
[email protected]
Recent Activity
new activity
about 3 hours ago
allura-forge/Llama-3.3-8B-Instruct:Love it!
liked
a model
about 4 hours ago
allura-forge/Llama-3.3-8B-Instruct
Organizations
Love it!
#6 opened about 3 hours ago
by
unmodeled-tyler
liked
a
model
about 4 hours ago
reacted to
CRAFTFramework's
post with 🚀
about 4 hours ago
Post
47
🔧 Behind the Scenes
CRAFT development: Sun-Mon only (full-time job Wed-Sat). 48 projects completed solo.
The time constraint is the proof—if the methodology works under pressure, it works.
Beta: February 2026 → craftframework.ai
CRAFT development: Sun-Mon only (full-time job Wed-Sat). 48 projects completed solo.
The time constraint is the proof—if the methodology works under pressure, it works.
Beta: February 2026 → craftframework.ai
reacted to
tsungyi's
post with 🚀
about 4 hours ago
Post
54
Big news from CES — Cosmos Reason 2 is here — our most advanced reasoning vision-language model for physical AI, now topping the Physical AI Bench leaderboard🏆
shi-labs/physical-ai-bench-leaderboard
What’s new:
- Enhanced physical reasoning & spatio-temporal understanding
- Flexible deployment with 2B & 8B model sizes
- Long-context understanding (up to 256K tokens)
- Object detection with 2D/3D point localizations and trajectory data
- New Cosmos Cookbook Recipes for faster onboarding
Read the full blog 📖 https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning
Download Cosmos Reason 2 👉 nvidia/Cosmos-Reason2-8B
On top of Cosmos Reason 2, we also rolled out other new updates, including:
- Cosmos Predict 2.5 – Unified Text2World/Image2World/Video2World model for higher-quality synthetic video worlds
- Cosmos Transfer 2.5-2B – Lightweight, high-fidelity world-to-world translation with stronger physics alignment
- NVIDIA GR00T N1.6 – Open robot foundation model for general-purpose robotic learning and control, integrated with Cosmos Reason
Get Started with the Cosmos Cookbook 🧑🏻🍳 https://nvda.ws/4qevli8
What’s new:
- Enhanced physical reasoning & spatio-temporal understanding
- Flexible deployment with 2B & 8B model sizes
- Long-context understanding (up to 256K tokens)
- Object detection with 2D/3D point localizations and trajectory data
- New Cosmos Cookbook Recipes for faster onboarding
Read the full blog 📖 https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning
Download Cosmos Reason 2 👉 nvidia/Cosmos-Reason2-8B
On top of Cosmos Reason 2, we also rolled out other new updates, including:
- Cosmos Predict 2.5 – Unified Text2World/Image2World/Video2World model for higher-quality synthetic video worlds
- Cosmos Transfer 2.5-2B – Lightweight, high-fidelity world-to-world translation with stronger physics alignment
- NVIDIA GR00T N1.6 – Open robot foundation model for general-purpose robotic learning and control, integrated with Cosmos Reason
Get Started with the Cosmos Cookbook 🧑🏻🍳 https://nvda.ws/4qevli8
updated
14
models
about 7 hours ago
vanta-research/atom-80b
Text Generation
•
80B
•
Updated
•
4
•
3
vanta-research/atom-27b
Text Generation
•
27B
•
Updated
•
204
•
4
vanta-research/atom-v1-preview-12b
Text Generation
•
12B
•
Updated
•
285
•
5
vanta-research/atom-v1-preview-8b
Text Generation
•
8B
•
Updated
•
213
•
3
vanta-research/atom-olmo3-7b
Text Generation
•
7B
•
Updated
•
23
•
5
vanta-research/atom-v1-preview-4b
Text Generation
•
4B
•
Updated
•
851
•
7
vanta-research/scout-8b
8B
•
Updated
•
6
vanta-research/scout-4b
Text Generation
•
4B
•
Updated
•
1.52k
•
11
vanta-research/wraith-8b
Text Generation
•
8B
•
Updated
•
243
•
6
vanta-research/atom-astronomy-7b
Text Generation
•
7B
•
Updated
•
38
•
2
vanta-research/apollo-astralis-2
Text Generation
•
9B
•
Updated
•
2
vanta-research/apollo-astralis-4b
Text Generation
•
4B
•
Updated
•
51
•
6
vanta-research/apollo-v1-7b
Text Generation
•
Updated
•
41
•
2
vanta-research/apollo-astralis-8b
Text Generation
•
8B
•
Updated
•
816
•
11
replied to
Hellohal2064's
post
about 8 hours ago
Definitely going to check this out! I've been using llama.cpp on my spark but 2.5x inference speed up is huge. Thanks for sharing!
reacted to
Hellohal2064's
post with 🔥
about 8 hours ago
Post
70
🚀 Excited to share: The First vLLM container for NVIDIA DGX Spark!
I've been working on getting vLLM to run natively on the new DGX Spark with its GB10 Blackwell GPU (SM121 architecture). The results? 2.5x faster inference compared to llama.cpp!
📊 Performance Highlights:
• Qwen3-Coder-30B: 44 tok/s (vs 21 tok/s with llama.cpp)
• Qwen3-Next-80B: 45 tok/s (vs 18 tok/s with llama.cpp)
🔧 Technical Challenges Solved:
• Built PyTorch nightly with CUDA 13.1 + SM121 support
• Patched vLLM for Blackwell architecture
• Created custom MoE expert configs for GB10
• Implemented TRITON_ATTN backend workaround
📦 Available now:
• Docker Hub: docker pull hellohal2064/vllm-dgx-spark-gb10:latest
• HuggingFace: huggingface.co/Hellohal2064/vllm-dgx-spark-gb10
The DGX Spark's 119GB unified memory opens up possibilities for running massive models locally. Happy to connect with others working on the DGX Spark Blackwell!
I've been working on getting vLLM to run natively on the new DGX Spark with its GB10 Blackwell GPU (SM121 architecture). The results? 2.5x faster inference compared to llama.cpp!
📊 Performance Highlights:
• Qwen3-Coder-30B: 44 tok/s (vs 21 tok/s with llama.cpp)
• Qwen3-Next-80B: 45 tok/s (vs 18 tok/s with llama.cpp)
🔧 Technical Challenges Solved:
• Built PyTorch nightly with CUDA 13.1 + SM121 support
• Patched vLLM for Blackwell architecture
• Created custom MoE expert configs for GB10
• Implemented TRITON_ATTN backend workaround
📦 Available now:
• Docker Hub: docker pull hellohal2064/vllm-dgx-spark-gb10:latest
• HuggingFace: huggingface.co/Hellohal2064/vllm-dgx-spark-gb10
The DGX Spark's 119GB unified memory opens up possibilities for running massive models locally. Happy to connect with others working on the DGX Spark Blackwell!
-
- 2 replies