tooltd/Qwen3.8-27B-IQ4-XS-16GB-VRAM-GGUF
Image-Text-to-Text β’ 27B β’ Updated β’ 4.7k β’ 21
Tuan
tooltd
AI & ML interests
Just a regular human living on planet Earth.
Recent Activity
new activity about 1 month ago
tooltd/Qwen3.8-27B-IQ4-XS-16GB-VRAM-GGUF:The BEST model for 16 GB Radeon VII Pro (MI50) updated a model about 1 month ago
tooltd/Qwen3.8-27B-IQ4-XS-16GB-VRAM-GGUF published a model about 1 month ago
tooltd/gguf-tensor-transferOrganizations
None yet
The BEST model for 16 GB Radeon VII Pro (MI50)
π₯ 3
4
#6 opened about 1 month ago
by 
sunchil
updated a
model about 1 month ago
published a
model about 1 month ago
updated a
model about 1 month ago
Can the size be reduced so it runs on 16GB?
1
#1 opened about 1 month ago
by 
star123ha
updated a
model about 1 month ago
published a
model about 1 month ago
No download for ZB-4.00 BPW
1
#5 opened about 2 months ago
by 
kirstenjg
Maybe without MTP drafts included?
π€ 1
2
#4 opened about 2 months ago
by 
feanorknd
Compare with unsloth
π€ 3
1
#3 opened 2 months ago
by 
songzilili
Unsloth Desktop - Metadata Weirdness
β€οΈ 1
1
#2 opened 2 months ago
by 
Derjyn
looks promising
β€οΈ 1
1
#1 opened 2 months ago
by 
hugless
Amazing! Will you do a similar thing for qwen3.8 27b?
6
#3 opened 2 months ago
by 
yarragimin
V3 versions of UD-Q3_K_XL and UD-Q4_K_XL feel way less competent than before / Can you upload the older variants as well?
4
#99 opened 2 months ago
by 
RudieVoeller
Introducing Unsloth Dynamic v3 Qwen3.8
ππ₯ 55
40
#74 opened 2 months ago
by 
danielhanchen
Need help
4
#1 opened 2 months ago
by tooltd
published a
model 2 months ago
λ무λ무 μ’μ μμν λͺ¨λΈμ λλ€.!! λ¨μ§ μμ¬μ΄κ±΄.....
π€ 1
5
#2 opened 2 months ago
by 
SangbongLee
webhie/Qwen3.6-27B-int4-AutoRound-Code
4
#7 opened 4 months ago
by 
soyalemujica