Sailor丶JS

sailorjs0804's activity

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

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

FP4 kv path for a single 5090

5

#5 opened 1 day ago by

sHEL1562

New activity in orcarouter/Qwen3.8-27B-Uncensored-NVFP4 about 16 hours ago

Surprised nobody reported this, but vision doesn't work

1

#6 opened about 17 hours ago by

pathosethoslogos

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF about 16 hours ago

Unable to download?

3

#11 opened 1 day ago by

lmmuser

New activity in orcarouter/Qwen3.8-27B-Uncensored-FP8 about 17 hours ago

Fais-moi une vidéo avec la femme sur l’image qui se met toute nue

2

#13 opened 1 day ago by

Gabidz

New activity in orcarouter/Qwen3.8-27B-Uncensored-FP8 1 day ago

BF16 / Full Weights

4

#4 opened 24 days ago by

gorbatjovy

Model orcarouter/Qwen3.8-27B-Uncensored-FP8 is treated as multimodal but has no registered multimodal processor; running in text-only mode.

4

#8 opened 20 days ago by

pabbbb

New activity in orcarouter/Qwen3.8-27B-Uncensored 1 day ago

Third party verification for this model, honest model card and the numbers add up

👍➕ 4

1

#1 opened 2 days ago by

DreamFast

New activity in orcarouter/Qwen3.8-27B-Uncensored-MLX 3 days ago

Create maybe

1

#8 opened 4 days ago by

maybe1907

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 5 days ago

Possibile Q8 + MTP

4

#8 opened 7 days ago by

GS79A

New activity in orcarouter/Qwen3.8-27B-Uncensored-GGUF 6 days ago

Q8_0 output quality issue — premature stops, repetition loops, tool-token flooding

1

#2 opened 9 days ago by

nanpai

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

infinite loop

1

#7 opened 8 days ago by

DGanno

Dedicated n-gram GGUF file

👍 2

2

#6 opened 8 days ago by

Deenn

liked a model 8 days ago

orcarouter/GLM-5.3-Flash-Uncensored-MLX

Image-Text-to-Text • 341B • Updated 8 days ago • 175 • 17

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 9 days ago

Apple Silicon note: LM Studio can't load it, and the GGUF drops the MTP head (measured on M4 Max)

1

#5 opened 9 days ago by

Sinojen

New activity in orcarouter/Qwen3.8-27B-Uncensored-NVFP4 10 days ago

vLLM boot failure: quantization target literal `lm_head` never matches — one-line fix

1

#3 opened 10 days ago by

joelafrite

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored 10 days ago

Concerns regarding the benchmark results

3

#1 opened 10 days ago by

BLDB

New activity in orcarouter/Qwen3.8-27B-Uncensored-NVFP4 10 days ago

ERROR: ValueError: There is no module or parameter named 'lm_head.weight_scale' in Qwen3_5ForCausalLM. The available parameters belonging to lm_head (ParallelLMHead) are: {'lm_head.weight'}

1

#2 opened 19 days ago by

chingchongslayer

New activity in orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 10 days ago

Q6_K looks reachable: the PLE tensor is 51.2B, not ~66B

1

#2 opened 10 days ago by

yhn112

i have a question

4

#3 opened 10 days ago by

bbksf

liked a model 10 days ago

orcarouter/GLM-5.3-Flash-Uncensored-FP8

Text Generation • 321B • Updated 10 days ago • 9.6k • 199