All Qwen3 uploads updated with fixed chat templates!
pinnedπ
2
2
#14 opened 7 days ago
by
shimmyshimmer

Tensor 'token_embd.weight' (q4_K) (and 0 others) cannot be used with preferred buffer type CUDA_Host, using CPU instead
#15 opened 4 days ago
by
WBB2500
The chat template is still broken
2
#13 opened 14 days ago
by
ilintar
Second Update for QWEN3 AI
6
#12 opened 17 days ago
by
E7Reine

Latest updates?
π
12
8
#10 opened 26 days ago
by
Dampfinchen
Please quantize a Q5_K_S version
π
1
3
#9 opened 27 days ago
by
fakezeta
Not compatible with transformers library
3
#8 opened 28 days ago
by
Xeenxavier007
Crashes after several responses
13
#7 opened 28 days ago
by
urtuuuu
`UD-Q4_K_XL` or `Q4_K_M`?
15
#6 opened 28 days ago
by
pootow
128k version?
3
#5 opened 29 days ago
by
AlexBefest

UPDATE FIXED! Is lower quants usable now?
3
#4 opened 29 days ago
by
CHNtentes
Missing q8?
2
#3 opened 29 days ago
by
blueridanus
UPDATED FIXED!! Template problem?
12
#2 opened 29 days ago
by
Noonecares52647842
Add languages tag
#1 opened 29 days ago
by
de-francophones
