Fabian Heller

Ununnilium's activity

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

New activity in lukealonso/GLM-5.2-NVFP4 14 days ago

TP5 RTX 6000?

8

#1 opened 16 days ago by

jpsequeira

New activity in Ununnilium/Qwen3.6-27B-IQ4_XS-pure-GGUF about 1 month ago

is possible to create Qwen3.6-27B-IQ4_XS-pure-GGUF with MTP support?

3

#1 opened about 1 month ago by

vinimuchulski

New activity in deepseek-ai/DeepSeek-V4-Flash about 1 month ago

Running models with vLLM on the RTX Pro 6000 - SM120

👀👍 2

12

#28 opened about 2 months ago by

liku2001

published a model 2 months ago

Ununnilium/Qwen3.6-27B-IQ4_XS-pure-GGUF

27B • Updated Apr 25 • 1.26k • 20

updated a model 2 months ago

Ununnilium/Qwen3.6-27B-IQ4_XS-pure-GGUF

27B • Updated Apr 25 • 1.26k • 20

liked a model 10 months ago

Intel/Mistral-Small-3.2-24B-Instruct-2506-int4-AutoRound

2B • Updated Nov 1, 2025 • 468 • 5

New activity in Intel/Mistral-Small-3.2-24B-Instruct-2506-int4-AutoRound 10 months ago

Works good with vLLM, just no tool calling

1

#1 opened 10 months ago by

Ununnilium

New activity in QuantTrio/GLM-4.5-AWQ 11 months ago

How many GPU Memory AWQ need?

5

#1 opened 11 months ago by

hermitg

Does it possible to create a version without MTP layer to save some VRAM

👍 1

1

#3 opened 11 months ago by

adonishong