nvidia/Nemotron-Labs-Diffusion-14B-Base
Text Generation • 14B • Updated • 160 • 1
DedeProGames PRO
DedeProGames
AI & ML interests
Thinking and Agentic Finetuning
Recent Activity
liked a model 44 minutes ago
nvidia/Nemotron-Labs-Diffusion-14B-Base liked a model 44 minutes ago
nvidia/Nemotron-Labs-Diffusion-14B liked a model 44 minutes ago
nvidia/Nemotron-Labs-Diffusion-8BOrganizations
liked 5
models 44 minutes ago
nvidia/Nemotron-Labs-Diffusion-14B
Text Generation • 14B • Updated • 11 • 2
nvidia/Nemotron-Labs-Diffusion-8B
Text Generation • 8B • Updated • 12.5k • 2
nvidia/Nemotron-Labs-Diffusion-3B
Text Generation • 4B • Updated • 10.6k • 2
nvidia/Nemotron-Labs-Diffusion-3B-Base
Text Generation • 4B • Updated • 12.5k • 1
liked a
model about 1 hour ago
Update README.md
1
#1 opened about 22 hours ago
by DedeProGames
inclusionAI/Ring-2.6-1T
🚀 4
#9887 opened 5 days ago
by DedeProGames
liked 2
models 5 days ago
liked a
Space 5 days ago
updated a
Space 5 days ago
reacted to Imosu's post with 👀🔥 5 days ago
Post
3294
# ZeroGPU Hardware Mismatch: Why Am I Getting RTX PRO 6000 Blackwell MIG Instead of the Documented H200?
I recently ran into a surprising issue while debugging a Hugging Face ZeroGPU Space.
According to the Hugging Face ZeroGPU documentation, ZeroGPU is described as using NVIDIA H200-based resources, with configurations such as “large” and “xlarge” offering H200-class memory. However, when I printed the actual GPU information inside my Space, I got something different:
GPU: NVIDIA RTX PRO 6000 Blackwell Server Edition MIG 2g.48gb
Capability: (12, 0)
Torch: 2.8.0+cu128
CUDA: 12.8
This is not an H200. It appears to be a MIG slice of an RTX PRO 6000 Blackwell Server Edition GPU, with 48GB VRAM.
This difference matters. It is not just a cosmetic hardware-name issue.
In my case, the Space was running Qwen3-TTS and failed with:
CUDA error:
no kernel image is available for execution on the device
The issue appears related to GPU architecture compatibility. The app was using kernels-community/flash-attn3, which is generally aligned with Hopper-class GPUs such as H100/H200, but the actual device exposed to the Space was Blackwell with compute capability 12.0. As a result, CUDA kernels that might work on the expected H200 environment failed on the actual assigned GPU.
To be clear, I am not saying the RTX PRO 6000 Blackwell is a bad GPU. It is a newer architecture and may be powerful in many workloads. But it is not the same as H200, and the software ecosystem compatibility is different. For ML workloads, especially those relying on custom CUDA kernels, the exact GPU architecture matters a lot.
This raises a few questions:
Is Hugging Face ZeroGPU now assigning RTX PRO 6000 Blackwell MIG instances instead of H200 instances?
If yes, why is this not clearly documented?
I recently ran into a surprising issue while debugging a Hugging Face ZeroGPU Space.
According to the Hugging Face ZeroGPU documentation, ZeroGPU is described as using NVIDIA H200-based resources, with configurations such as “large” and “xlarge” offering H200-class memory. However, when I printed the actual GPU information inside my Space, I got something different:
GPU: NVIDIA RTX PRO 6000 Blackwell Server Edition MIG 2g.48gb
Capability: (12, 0)
Torch: 2.8.0+cu128
CUDA: 12.8
This is not an H200. It appears to be a MIG slice of an RTX PRO 6000 Blackwell Server Edition GPU, with 48GB VRAM.
This difference matters. It is not just a cosmetic hardware-name issue.
In my case, the Space was running Qwen3-TTS and failed with:
CUDA error:
no kernel image is available for execution on the device
The issue appears related to GPU architecture compatibility. The app was using kernels-community/flash-attn3, which is generally aligned with Hopper-class GPUs such as H100/H200, but the actual device exposed to the Space was Blackwell with compute capability 12.0. As a result, CUDA kernels that might work on the expected H200 environment failed on the actual assigned GPU.
To be clear, I am not saying the RTX PRO 6000 Blackwell is a bad GPU. It is a newer architecture and may be powerful in many workloads. But it is not the same as H200, and the software ecosystem compatibility is different. For ML workloads, especially those relying on custom CUDA kernels, the exact GPU architecture matters a lot.
This raises a few questions:
Is Hugging Face ZeroGPU now assigning RTX PRO 6000 Blackwell MIG instances instead of H200 instances?
If yes, why is this not clearly documented?
- 2 replies
More Benchmarks
1
#5 opened 6 days ago
by 
thomasmaindron
posted an update 7 days ago
Post
155
🚀 Introducing the GRM-2.6 Family
The GRM-2.6 family is a new generation of reasoning-focused models from Orion LLM Labs, built for difficult tasks, coding, STEM, terminal agents, and advanced local AI workflows.
GRM-2.6-Plus is the main high-capability model in the family: a 27B-class reasoning model based on Qwen3.6, designed for strong structured reasoning, coding, agentic use, and practical local deployment.
GRM-2.6-Opus builds on GRM-2.6-Plus as a merge with an Opus-style reasoning distilled model, improving structured reasoning behavior, terminal-agent workflows, coding ability, and complex problem solving.
Both models are designed for users who want powerful reasoning models that remain practical for research, local inference, coding, and agent experiments.
Models:
GRM-2.6-Plus: OrionLLM/GRM-2.6-Plus
GRM-2.6-Opus: OrionLLM/GRM-2.6-Opus
Organization:
OrionLLM
The GRM-2.6 family is a new generation of reasoning-focused models from Orion LLM Labs, built for difficult tasks, coding, STEM, terminal agents, and advanced local AI workflows.
GRM-2.6-Plus is the main high-capability model in the family: a 27B-class reasoning model based on Qwen3.6, designed for strong structured reasoning, coding, agentic use, and practical local deployment.
GRM-2.6-Opus builds on GRM-2.6-Plus as a merge with an Opus-style reasoning distilled model, improving structured reasoning behavior, terminal-agent workflows, coding ability, and complex problem solving.
Both models are designed for users who want powerful reasoning models that remain practical for research, local inference, coding, and agent experiments.
Models:
GRM-2.6-Plus: OrionLLM/GRM-2.6-Plus
GRM-2.6-Opus: OrionLLM/GRM-2.6-Opus
Organization:
updated a
model 9 days ago
Update .eval_results/gpqa.yaml
#1 opened 9 days ago
by DedeProGames
Update .eval_results/gpqa_diamond.yaml
#1 opened 9 days ago
by DedeProGames
Create preprocessor_config.json
#4 opened 9 days ago
by 
willfalco