Qwen3.5 GGUF Evaluation Results
pinned👍 6
9
#9 opened 2 months ago
by
danielhanchen
Q3_K_XL works surprisingly fast for 3x3090 + 128 ram
pinned🔥 8
7
#4 opened 2 months ago
by
fizzacles
Thank you! The UD-IQ2_M quant is amazing.
#23 opened 6 days ago
by
x-polyglot-x
Re-generate GGUFs to benefit from 10% speedup
2
#22 opened about 1 month ago
by
tarruda
No UD-IQ1_S after the update?
#21 opened about 1 month ago
by
RazielAU
UD confusion
2
#20 opened about 1 month ago
by
inputout
please restore the TQ1_0 model
👀👍 3
4
#19 opened about 1 month ago
by
lefromage
Old UD quants gone?
😔 1
#18 opened about 1 month ago
by
TK-13
Mac M3 Ultra 256GB
1
#16 opened about 2 months ago
by
ragallo
Do the 397B quants need to be downloaded again?
➕ 1
2
#15 opened about 2 months ago
by
whoisjeremylam
Is there any content questioning restriction for this?
#14 opened about 2 months ago
by
zhangxianguang
keep crashing on llama.cpp
#13 opened about 2 months ago
by
rosspanda0
Very impressed by Qwen3.5-397B-A17B-UD-TQ1_0.gguf quant
❤️ 1
2
#12 opened about 2 months ago
by
dzupin
How to enable vision encoder?
1
#10 opened 2 months ago
by
stefan28123
Is it possible to turn off thinking mode on Llama.cpp?
4
#8 opened 2 months ago
by
alexaione
CUDA error: an illegal memory access was encountered for UD-Q8_K_XL/Qwen3.5-397B-A17B-UD-Q8_K_XL-00001-of-00011.gguf
2
#7 opened 2 months ago
by
CHONGYOEYAT
request: Standalone notebook for Unsloth Dynamic Quant 2.0 (GGUF export)
#6 opened 2 months ago
by
rikunarita
Quant comparison versus "smol-IQ2_XS"
4
#5 opened 2 months ago
by
coder543
Core dumped for me,
7
#3 opened 2 months ago
by
aaron-newsome
How to choose MXFP4 vs Q4_K_XL on CPU + CUDA
2
#1 opened 2 months ago
by
SlavikF