John
cmp-nct
AI & ML interests
None yet
Recent Activity
new activity
about 8 hours ago
zai-org/GLM-4.7-Flash:llama.cpp inference - 20 times (!) slower than OSS 20 on a RTX 5090
new activity
about 1 month ago
unsloth/Nemotron-3-Nano-30B-A3B-GGUF:Should UD-Q6_K_XL identical to Q6_K.gguf?
Organizations
llama.cpp inference - 20 times (!) slower than OSS 20 on a RTX 5090
7
#12 opened about 10 hours ago
by
cmp-nct
Interesting model - how to control reasoning length?
#2 opened 3 days ago
by
cmp-nct
Should UD-Q6_K_XL identical to Q6_K.gguf?
5
#1 opened about 1 month ago
by
BVEsun
Quantizations below 4 bit are bad
1
#4 opened about 1 month ago
by
cmp-nct
Good model but it is very flawed in recalling input
6
#5 opened about 1 month ago
by
cmp-nct
No space to test it, not on open router, are there obstacles ?
2
#9 opened 3 months ago
by
cmp-nct
Kernel assertion errors on 5090 using generation with MXfp4 (gpt-oss) - (stable on 4090)
5
#1 opened 5 months ago
by
cmp-nct
Creating quantization
#4 opened 5 months ago
by
cmp-nct
This model is not much better than qwen3 32b for writing code
👍
3
9
#4 opened 6 months ago
by
xldistance
Wan't to share my Training-Set
3
#4 opened 7 months ago
by
havok2
Very good results
3
#5 opened 7 months ago
by
cmp-nct
Multiple languages support
👀
👍
15
6
#19 opened 9 months ago
by
thunder-007
Interesting idea, what about multi lingual prompts ?
➕
3
3
#7 opened 9 months ago
by
cmp-nct
Gguf?
👍
8
8
#2 opened 11 months ago
by
AlgorithmicKing
Safety
👍
1
6
#21 opened 12 months ago
by
Javier81k
Modl showing up as Llama instead of phi3 in LMstudio
12
#1 opened over 1 year ago
by
Tirin
gguf / llama.cpp support
2
#45 opened over 1 year ago
by
cmp-nct
Using gguf format
🤝
2
7
#1 opened over 1 year ago
by
Tomy99999