Smith

Hector111's activity

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

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF 6 days ago

Regardless of VRAM, which is the best MTP version GGUF model?

👍 1

4

#5 opened 6 days ago by

Hector111

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GGUF 7 days ago

why Qwen3.6-27B-uncensored-heretic-v2-GGUF models are deleted？

❤️➕ 2

4

#3 opened 7 days ago by

Hector111

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2-NVFP4-GGUF 9 days ago

which kl divergence is lower between Qwen3.6-27B-uncensored-heretic-v2-NVFP4-MLP.gguf and Qwen3.6-27B-uncensored-heretic-v2-Q8_0.gguf

1

#1 opened 9 days ago by

Hector111

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2-FP8-W8A16 12 days ago

The fp8 version is not supported on vllm or sglang

5

#1 opened 13 days ago by

Hector111

New activity in llmfan46/Qwen3.6-27B-uncensored-heretic-v2 13 days ago

Hello, could you please provide an FP8 quantized version of the model?

3

#4 opened 13 days ago by

Hector111

New activity in unsloth/Qwen3.6-27B-GGUF 20 days ago

What are the differences between ud version and not ud version？

2

#13 opened 20 days ago by

Hector111