Monke
paragon-of-brah
·
AI & ML interests
None yet
Organizations
None yet
Qwen4 with Various Sizes?
❤️ 2
1
#25 opened 3 months ago
by
Duonglv
Changing reasoning effort requires rebuilding whole kv cache
👍 1
2
#36 opened 3 months ago
by
paragon-of-brah
Completely unusable with TP=2
1
#5 opened 5 months ago
by
Dsturb
Safetensors version for MLX / oMLX users
1
#4 opened 5 months ago
by
henryxwong
Which build for dflash?
5
#3 opened 5 months ago
by
Trilogix1
how Q2_K so small
2
#2 opened 5 months ago
by
CHHORVORN
128GB Strix Halo
3
#1 opened 5 months ago
by
neoOpus
I once again, ask for your support (if possible)
12
#2 opened 5 months ago
by
InfernalDread
GGUFs of 397B
👍 4
9
#1 opened 5 months ago
by
DrRos
Help a newbie understand - which version for 2 x RTX 6000 Pro
2
#6 opened 5 months ago
by
peter-storm
427B params? This is not intelligence, its brute force.
👀😔 4
17
#6 opened 5 months ago
by
Nerdsking
thinking tag present in the claude code ik_llama.cpp
4
#5 opened 5 months ago
by
gopi87
Can you create a GGUF quantization of the iq1_m model?
2
#2 opened 5 months ago
by
xldistance
thinking tag fix
5
#3 opened 5 months ago
by
gopi87
What a Monster. It is very good...
🔥 4
23
#5 opened 6 months ago
by
Hunterx
model is crshing in ik_llama.cpp any help
7
#1 opened 5 months ago
by
gopi87
model is crshing in ik_llama.cpp any help
7
#1 opened 5 months ago
by
gopi87
Can you create a GGUF quantization of the iq1_m model?
2
#2 opened 5 months ago
by
xldistance
What a Monster. It is very good...
🔥 4
23
#5 opened 6 months ago
by
Hunterx
What a Monster. It is very good...
🔥 4
23
#5 opened 6 months ago
by
Hunterx