Henry

hdnh2006's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in RedHatAI/Qwen3.6-35B-A3B-NVFP4 21 days ago

MTP is slower than the "normal" serve

4

#10 opened about 1 month ago by

hdnh2006

New activity in NeuralNet-Hub/Qwen3.6-27B-NVFP4 28 days ago

NVFP4 on RTX 5090: 120k Context & 8-bit KV Cache Feasibility

1

#1 opened about 1 month ago by

nsfilho

New activity in wangzhang/gemma-4-31B-it-abliterated 29 days ago

processor_config.json file upload for smooth integration with vLLM

#5 opened 29 days ago by

hdnh2006

New activity in wangzhang/gemma-4-26B-A4B-it-abliterix 29 days ago

Recommend to upload process_config.json from original model

1

#7 opened 29 days ago by

hdnh2006

This PR uploads the process_config.json file allowing to serve the model using vLLM without issues

#8 opened 29 days ago by

hdnh2006

New activity in cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF about 1 month ago

llama.cpp version?

1

#5 opened about 1 month ago by

hdnh2006

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking about 1 month ago

vLLM version? I am getting error with some layers

2

#6 opened about 1 month ago by

hdnh2006

New activity in AEON-7/Gemma-4-31B-it-DECKARD-HERETIC-Uncensored-NVFP4 about 1 month ago

After applying patch, the model is unable to serve

#3 opened about 1 month ago by

hdnh2006

New activity in AEON-7/Gemma-4-26B-A4B-it-Uncensored-NVFP4 about 1 month ago

This model is not uncensored at all

1

#2 opened about 1 month ago by

hdnh2006

New activity in unsloth/Qwen3.6-27B-NVFP4 about 1 month ago

Why is it too big?

➕ 3

9

#1 opened about 2 months ago by

alexcardo

MTP?

➕ 4

3

#3 opened about 1 month ago by

tyapo

Impossible to run in a 5090 with any context window, no even 8192.

2

#2 opened about 1 month ago by

hdnh2006

New activity in Jiunsong/supergemma4-26b-abliterated-multimodal about 1 month ago

vLLM is unable to deploy this model

#3 opened about 1 month ago by

hdnh2006

New activity in DreamFast/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark about 1 month ago

NVFP4 version?

3

#3 opened about 1 month ago by

hdnh2006

New activity in DreamFast/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark about 1 month ago

Include visual layers in `model.safetensors.index.json `

#1 opened about 1 month ago by

hdnh2006

New activity in RedHatAI/gemma-4-26B-A4B-it-NVFP4 about 2 months ago

Impossible to deploy using vLLM 0.20.0

2

#6 opened about 2 months ago by

hdnh2006

New activity in HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive 2 months ago

safetensor?

👀 3

10

#4 opened 2 months ago by

MRU4913

New activity in Qwen/Qwen3.5-35B-A3B-GPTQ-Int4 4 months ago

Working vLLM setup on RTX 5090 — 194-197 tok/s with image/video

👍🚀 2

5

#3 opened 4 months ago by

8055izham

New activity in unsloth/Qwen3.5-35B-A3B-GGUF 4 months ago

Is there some helpful regex to offload all MoE layers to the CPU?

4

#7 opened 4 months ago by

hdnh2006

New activity in zai-org/GLM-4.7-Flash 5 months ago

Off reasoning

👀 2

4

#56 opened 5 months ago by

kmahdi