lychee888/Qwen3.8-Flash-Next-Uncensored-NVFP4-FP8PLE
Image-Text-to-Text • 180B • Updated • 1.22k • 8
B F
lightenup
AI & ML interests
None yet
Recent Activity
liked a model 9 days ago
lychee888/Qwen3.8-Flash-Next-Uncensored-NVFP4-FP8PLE new activity 28 days ago
turboderp/Qwen3.8-Flash-Next-exl3:ngram at bf16? liked a model about 1 month ago
local-inference-lab/Qwen3.8-Flash-Next-NVFP4Organizations
None yet
liked a
model 9 days ago
ngram at bf16?
➕ 1
6
#12 opened 29 days ago
by 
nnnig
liked 2
models about 1 month ago
liked 2
models about 2 months ago
31B-Dense model missing from HuggingFace
👍👀 28
15
#2 opened 4 months ago
by 
smcleod
Mar 5 Update: New iMatrix + Variants
❤️ 6
4
#20 opened 7 months ago
by 
danielhanchen
Update status for Qwen3.5 122B and 27B GGUFs?
👍👀 23
6
#13 opened 7 months ago
by 
Chlheng
what's this?
11
#1 opened 8 months ago
by 
Simon716
liked a
model 8 months ago
recommended vllm tool call parser?
👀 1
6
#17 opened 8 months ago
by lightenup
local setup with a coding agent
👍👀 6
3
#15 opened 8 months ago
by lightenup
Very specific json formatting issue in tool calls
➕ 1
4
#14 opened 8 months ago
by deleted
Inconsistent output (resolved)
5
#2 opened 8 months ago
by 
nephepritou
Single RTX Pro 6000 users
4
#1 opened 8 months ago
by lightenup
cost estimates?
4
#5 opened 10 months ago
by lightenup
I agree with the statement that local, open-source models will eventually win.
I don't think that latency and real-time control are the major driver towards that future, but privacy and agency might be.
LoRA adapter?
#3 opened about 1 year ago
by lightenup
Performance? Methodology?
5
#2 opened about 1 year ago
by lightenup