Y Tan

YTan2000's activity

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

New activity in YTan2000/Ornith-1.5-35B-A3B-TQ3_4S 19 days ago

Slow speed

1

#1 opened 19 days ago by

asdflam

New activity in YTan2000/Ornith-1.0-35B-TQ3_4S 19 days ago

Will this work with 16 GB VRAM?

5

#2 opened 2 months ago by

cnsiva

New activity in YTan2000/Muse-Glimmer-30B-TQ3_4S 29 days ago

Model Crashes

1

#1 opened 29 days ago by

jacquesbezuidenhout

New activity in YTan2000/Qwen3.6-35B-A3B-TQ3_4S about 1 month ago

Degenerative looping on hermes agent

4

#7 opened about 1 month ago by

ahmedsevenup

New activity in YTan2000/Ornith-1.0-35B-TQ3_4S 2 months ago

mmproj ?

1

#1 opened 3 months ago by

sean73777

New activity in YTan2000/Qwen3.6-27B-TQ3_4S 3 months ago

Does it support MTP?

2

#6 opened 4 months ago by

jian2023

New activity in YTan2000/Qwen3.6-35B-A3B-MTP-TQ3_4S 4 months ago

Any plans to add qwopus3.6-35b ?

4

#5 opened 4 months ago by

kyunle

Updating to master brakes PP

14

#4 opened 4 months ago by

kyunle

Repo doesn't build

4

#2 opened 4 months ago by

gdevenyi

Build error

6

#3 opened 4 months ago by

njtu0308

New activity in YTan2000/Qwen3.6-27B-TQ3_4S 4 months ago

Can I use this model with TurboQuant 4bit KV cache in your llama.cpp runtime fork?

3

#2 opened 5 months ago by

Gavin-chen

New activity in YTan2000/Qwen3.6-35B-A3B-MTP-TQ3_4S 4 months ago

mmproj supported?

2

#1 opened 4 months ago by

gdevenyi

New activity in YTan2000/Qwen3.6-27B-TQ3_4S 4 months ago

Status with rotorquant and installation method on CachyOS and 5060Ti 16GB GPU

11

#5 opened 4 months ago by

omarroshdi

New activity in YTan2000/Qwopus3.5-27B-v3-Abliterated-TQ3_4S 5 months ago

VRAM usage, quantization & Context length

9

#1 opened 5 months ago by

cnsiva

New activity in YTan2000/Qwen3.6-35B-A3B-TQ3_4S 5 months ago

Unable to load using LMStudio

2

#2 opened 5 months ago by

Idigovinda

Model won't load on MacOS LM Studio / llama-server

2

#5 opened 5 months ago by

AlexsJones

Any plans to release quantizer or quantize other models?

5

#4 opened 5 months ago by

kyunle

llama.cpp-hip-turboquant — ROCm port of the TurboQuant fork (turbo-tan) for AMD RX 7900 XTX

4

#1 opened 5 months ago by

flamme-demon

After the model is loaded, tool_calls cannot be used properly during operation

4

#3 opened 5 months ago by

clonek

New activity in YTan2000/Qwen3.5-27B-TQ3_1S 5 months ago

mmproj

🤝 1

4

#1 opened 6 months ago by

linkpharm