Sailor丶JS

sailorjs0804's activity

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

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 2 days ago

Can you please update the MTP draft model to be compatible with current llama.cpp upstream?

1

#17 opened 2 days ago by

igzbar

New activity in orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF 3 days ago

Could you please tell me the differences between this version and Qwen 3.8-27B-Uncensored-GGUF?

4

#1 opened 12 days ago by

EurusWine

New activity in orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF 5 days ago

I apologize for the inconvenience, but would it be possible to work on this model?

1

#8 opened 6 days ago by

suitup91

New activity in orcarouter/GLM-5.3-Flash-Uncensored-GGUF 8 days ago

rename glm5next to glm5-next

6

#4 opened 11 days ago by

ZHUOZA

New activity in orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF 8 days ago

OrcaSAQ2 Cyber 27B reached 68 tok/s and 240K context on 2× RTX 3060 12GB

👍 1

2

#4 opened 9 days ago by

SpaceMo0

New activity in orcarouter/Qwen3.8-27B-Uncensored-GGUF 8 days ago

NOT UNCENSORED

2

#5 opened 12 days ago by

darkarra

New activity in orcarouter/OrcaSAQ-2-27B 16 days ago

GGUF please

❤️ 6

4

#3 opened 16 days ago by

anubhav200

New activity in orcarouter/Qwen3.8-27B-Uncensored-GGUF 16 days ago

orcarouter/Qwen3.8-27B-Uncensored-GGUF

👍 12

4

#4 opened about 1 month ago by

Scripteaser

New activity in orcarouter/OrcaSAQ-2-27B 16 days ago

When AMD support

2

#1 opened 17 days ago by

TILK

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-NVFP4 21 days ago

Can it run on a configuration of 4*5090?

1

#4 opened 21 days ago by

zhnagchenchne

New activity in orcarouter/Qwen3.8-27B-Uncensored-MLX 21 days ago

Create Qwen3.8-27B-Uncensored-MLX-q6

#11 opened 21 days ago by

ljl137

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 21 days ago

Qwen3.8-Flash-Next iQ3_M GGUF: MTP achieves ~60% acceptance but is slower than non-speculative decoding on a single RTX 5090

👍 2

2

#16 opened 22 days ago by

Turkinolith

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

Could you build a V100/SM70-compatible NVFP4 (modelopt) variant?

👀 1

3

#3 opened 25 days ago by

DAPXDAP

New activity in orcarouter/GLM-5.3-Flash-Uncensored-FP8 25 days ago

Thank you! =D

#3 opened 26 days ago by

michael-hinck

New activity in orcarouter/Qwen3.8-27B-Uncensored-MLX 25 days ago

Bug in the model

7

#9 opened 27 days ago by

MoneyKen

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 26 days ago

test

#14 opened 26 days ago by

Turboaitech

KLD/PPL Calculations Request

1

#13 opened 27 days ago by

feal87

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 30 days ago

Severe performance regression vs. unsloth's GGUF on identical hardware/config — likely tensor/metadata mismatch for MoE expert offloading

7

#12 opened about 1 month ago by

luphaxio

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF about 1 month ago

Q8 has a tensor count issue.

4

#9 opened about 1 month ago by

mvalley

New activity in orcarouter/GLM-5.3-Flash-Uncensored-NVFP4 about 1 month ago

RuntimeError: Worker failed with error 'concat_and_cache_mla

3

#3 opened about 1 month ago by

hdnh2006