pathosethoslogos

pathosethoslogos's activity

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

New activity in DavidAU/Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic 18 days ago

New 'ToMoE' approach, converting dense model to MoE model -- what do you think about Qwen3.8-27B -> 40B -> ToMoe (e.g. A10B) -> n-grams -> quant-aware NVFP4 quantisation?

👍❤️ 1

#10 opened 18 days ago by

pathosethoslogos

This thing is bizarre

3

#9 opened about 2 months ago by

Exxt

New activity in inclusionAI/Ling-3.0-flash-Fin 19 days ago

fp4 release of Fin like Ling-3.0-flash-fp4?

4

#1 opened about 1 month ago by

pathosethoslogos

New activity in nvidia/Qwen3.8-Flash-Next-NVFP4 23 days ago

Quant requests?

2

#5 opened about 1 month ago by

pathosethoslogos

New activity in inclusionAI/Ling-3.0-flash-Fin-fp4 24 days ago

Your Fin quants aren't being listed as quants for the base model on HF

#2 opened 24 days ago by

pathosethoslogos

Causing machine the hang + then vLLM eventually to crash

#1 opened 24 days ago by

pathosethoslogos

New activity in deepseek-ai/DeepSeek-V4.1-Flash 25 days ago

DeepSeek V4.1 Flash Lite

➕👍 36

16

#11 opened about 1 month ago by

KeinNiemand

New activity in QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 29 days ago

This model keeps quitting mid-way and/or doesn't answer

15

#6 opened about 1 month ago by

pathosethoslogos

New activity in nvidia/Qwen3.8-27B-NVFP4 about 1 month ago

Probably the best NVFP4 model, but it still goes crazy

1

#6 opened about 1 month ago by

pathosethoslogos

New activity in orcarouter/Qwen3.8-27B-Uncensored-NVFP4 about 1 month ago

Surprised nobody reported this, but vision doesn't work

4

#6 opened about 1 month ago by

pathosethoslogos

New activity in inclusionAI/Ling-3.0-flash-VL-fp8 about 1 month ago

Artificial Analysis Intelligence Index image

3

#4 opened about 1 month ago by

pathosethoslogos

New activity in inclusionAI/Ling-3.0-flash about 1 month ago

Any plans for merging into mainline vLLM?

➕ 1

2

#16 opened about 1 month ago by

pathosethoslogos

New activity in RadixArk/GLM-5.3-NVFP4 about 1 month ago

Quant requests?

#4 opened about 1 month ago by

pathosethoslogos

New activity in peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF about 1 month ago

The ONLY annoying thing about this model

12

#11 opened about 1 month ago by

Azula39

New activity in unsloth/Qwen3.8-27B-NVFP4 about 1 month ago

Quant requests?

#25 opened about 1 month ago by

pathosethoslogos

New activity in QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 about 1 month ago

Quant request?

🔥 1

2

#5 opened about 1 month ago by

pathosethoslogos

New activity in RadixArk/Qwen3.8-Flash-Next-NVFP4 about 1 month ago

One-command deployment on a single DGX Spark (34-42 tok/s, prefix caching, 262K)

👍🔥 2

5

#7 opened about 1 month ago by

hasanbasbunar

New activity in unsloth/Qwen3.8-27B-unsloth-bnb-4bit about 1 month ago

No explanation on what 'bnb' is in the model card

👍 3

1

#2 opened about 1 month ago by

pathosethoslogos

New activity in z-lab/Qwen3.8-27B-DFlash2 about 1 month ago

When will this DFlash model be compatible or come to mainline vLLM Git?

#12 opened about 1 month ago by

pathosethoslogos

New activity in incoai/Qwen3.8-27B-DFlash2 about 2 months ago

When will it come to mainline vLLM Git?

#7 opened about 2 months ago by

pathosethoslogos