ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
Image-Text-to-Text • 27B • Updated • 207k • 267
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
Maybe add vLLM FP8 KVCache calibration scales?
1
#3 opened 1 day ago
by 
ibaldonl
request for qwen3.8 next
🚀 1
7
#3 opened 5 days ago
by 
Chillzyg
Would you consider GSQ-RCO IQ3_S + MTP for a Qwen3.8-27B coding-focused fine-tune?
2
#8 opened about 23 hours ago
by 
Schestex
It is recommended to use IQ3_S-MTP for better instruction following and programming capabilities.
🔥 6
2
#7 opened 3 days ago
by 
qwased
Mtp integrated version coming?
🚀 3
11
#4 opened 5 days ago
by 
CheesingGouda
Plans to upstream this patch in vLLM?
1
#2 opened 2 days ago
by ibaldonl
can add gguf for us, please?
1
#1 opened 2 days ago
by 
xizonghu
helcig
updated a
model 2 days ago
Bigger version?
🚀 1
4
#2 opened 5 days ago
by 
smol-computer
Mtp integrated version coming?
🚀 3
11
#4 opened 5 days ago
by CheesingGouda
Bigger version?
🚀 1
4
#2 opened 5 days ago
by smol-computer
Please keep the MTP/nextn tensors — and consider a ~3.25 bpw target
🧠➕ 8
4
#1 opened 6 days ago
by 
palmanza
anm2211
updated a
model 5 days ago
helcig
published a
model 7 days ago
helcig
updated a
collection 7 days ago
This result is so exciting — has anyone done a full benchmark test on it?
👍 1
3
#1 opened 8 days ago
by 
modderbug
helcig
authored 2
papers 10 days ago
anm2211
updated a
collection 13 days ago