no
Rotating
AI & ML interests
None yet
Recent Activity
new activity
about 18 hours ago
unsloth/GLM-4.7-GGUF:"model has unused tensor" on UD-IQ2_M
new activity
3 days ago
unsloth/Qwen-Image-Edit-2511-GGUF:They sent us a Christmas turkey.
Organizations
None yet
"model has unused tensor" on UD-IQ2_M
1
#4 opened 1 day ago
by
tarruda
They sent us a Christmas turkey.
2
#1 opened 3 days ago
by
Rotating
fp8 text encoder pls
2
#23 opened 29 days ago
by
JorG941
No thinking tags when it runs?
13
#1 opened about 2 months ago
by
Disdrix
Quantization destroyed coding abilities in Q5 (735Gb RAM)
17
#4 opened about 2 months ago
by
krustik
Fingers crossed for the 4.6-air
➕
❤️
6
14
#1 opened 3 months ago
by
aaron-newsome
Quants without imatrix
17
#2 opened 3 months ago
by
Rotating
Version Q4 K XL works great with llama.cpp
🔥
1
2
#3 opened 5 months ago
by
jeffwadsworth
Update the instructions on requirements
2
#10 opened 5 months ago
by
segmond
Update - Tool Calling + Chat Template bug fixes
9
#20 opened 7 months ago
by
danielhanchen
Please share feedback here!
34
#6 opened 7 months ago
by
shimmyshimmer
invalid model: tensor 'blk.25.ffn_gate_exps.weight' is duplicated
2
#12 opened 7 months ago
by
Rotating
DOA
👍
1
15
#1 opened 9 months ago
by
MrDevolver
671B params or 685B params?
6
#8 opened 9 months ago
by
createthis
Would There be Dynamic Qunatized Versions like 2.51bit
8
#1 opened 9 months ago
by
MotorBottle
Something wrong
12
#3 opened 10 months ago
by
wcde
Q2_K_XL model is the best? IQ2_XXS is better than Q2_K_XL in mmlu-pro benchmark
11
#36 opened 10 months ago
by
albertchow
is it uncensored?
5
#33 opened 10 months ago
by
Morrigan-Ship
when using with ollama, does it support kv_cache_type=q4_0 and flash_attention=1?
3
#28 opened 11 months ago
by
leonzy04