A

batsclamp's activity

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

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 11 days ago

Quality metrics on DGX Spark (GB10)

👍 1

2

#4 opened 12 days ago by

batsclamp

New activity in Jackrong/Qwopus3.6-27B-v2-FP8 11 days ago

best model on DGX Spark

👍 1

#4 opened 11 days ago by

batsclamp

New activity in nvidia/Qwen3.6-27B-NVFP4 24 days ago

this model hallucinates easily

1

#13 opened 24 days ago by

batsclamp

Does it support MTP?

➕👍 3

4

#6 opened 25 days ago by

sharon8811

New activity in froggeric/Qwen-Fixed-Chat-Templates about 1 month ago

Non-thinking generation prompt uses non-canonical `<think>\n</think>\n` → duplicated output under streaming

6

#43 opened about 1 month ago by

batsclamp

New activity in sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP 3 months ago

Overall best abliterated model to currnetly use on DGX Spark

👍 1

#4 opened 3 months ago by

batsclamp

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 3 months ago

The DGX Spark didn't reach the benchmark speed.

9

#5 opened 3 months ago by

ohuihui

New activity in batsclamp/Huihui-Qwen3.6-35B-A3B-abliterated-FP8 3 months ago

The Response of model is Empty

4

#1 opened 3 months ago by

Philip12sdf

New activity in huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated 3 months ago

Please upload a version of fp8 model Weight

2

#1 opened 3 months ago by

Philip12sdf

New activity in huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated 3 months ago

weights are missing. Upload bug?

2

#1 opened 3 months ago by

batsclamp

New activity in batsclamp/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-FP8 3 months ago

garbled characters.

1

#2 opened 3 months ago by

Atituiset

New activity in batsclamp/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-FP8 4 months ago

VLLM 0.18.0 Fails to Disable Thinking Mode for Qwen3.5-35B-A3B-FP8

3

#1 opened 4 months ago by

huang123chuan

New activity in RedHatAI/Qwen3.5-122B-A10B-NVFP4 4 months ago

Use Qwen2TokenizerFast tokenizer class for vllm support

👍 2

1

#1 opened 4 months ago by

romaai