Victor C.
dehnhaide
AI & ML interests
None yet
Recent Activity
new activity about 17 hours ago
AesSedai/Step-3.5-Flash-GGUF:Step-3.5 Flash Midtrain GGUF liked a model 4 days ago
stepfun-ai/Step-3.7-Flash-GGUF liked a model 5 days ago
AesSedai/Step-3.7-Flash-GGUFOrganizations
Step-3.5 Flash Midtrain GGUF
5
#6 opened 3 days ago
by
Anaya3D
New quants IQ4_XS isn't loaded by llama.cpp(b9050) with segfault issue
12
#8 opened 27 days ago
by
smalinin
Works great with your PR 22493!
❤️ 2
10
#1 opened about 1 month ago
by
Mdubbya
Excellent 5.00 bps quant
#2 opened about 2 months ago
by
dehnhaide
Hoping for your magic on MiniMax-M2.7-FP8-INT4-AWQ quant
17
#2 opened about 2 months ago
by
dehnhaide
Testing Q5 flavors (ubergarm / aessedai / unsloth) for "speed" on 8x RTX 3090
🔥 1
2
#10 opened about 2 months ago
by
dehnhaide
UD-Q4_K_XL of MiniMax-M2.7-GGUF in BROKEN
8
#5 opened about 2 months ago
by
dehnhaide
An upgrade in quality and a mixed bag of ... 8x RTX3090
1
#3 opened about 2 months ago
by
dehnhaide
GLM 5.1 vs GLM 5 - burns A LOT output tokens on thinking
👍 1
35
#6 opened about 2 months ago
by
curiouspp8
Question about benchmark results
🔥🚀 2
8
#5 opened 3 months ago
by
tarruda
Need a 5% and 15% REAP
7
#10 opened about 2 months ago
by
nawoalanor
GGUF quants available — all sizes Q2_K through Q8_0 + BF16
🚀❤️ 1
2
#8 opened about 2 months ago
by
dennny123
I'm on waiting list for AesSedai Minimax M2.7 Q4_K_M or similar...
❤️ 1
4
#3 opened 3 months ago
by
MartinPatterson
Testing smol-IQ5_KS
4
#13 opened about 2 months ago
by
shewin
Model seems to have issues in vLLM (characters duplication)
🔥 1
8
#15 opened 2 months ago
by
dehnhaide
Check out Thireus GGUF-Tool-Suite quants!
❤️🤗 5
8
#13 opened 2 months ago
by
ubergarm
Quant HAS issues + results with vLLM on 8x 3090
4
#1 opened 2 months ago
by
dehnhaide
accuracy
26
#4 opened 4 months ago
by
ktsaou
Offloading layers is not working for me
9
#9 opened 2 months ago
by
tnuvkeg
AesSedai/Kimi-K2.5-GGUF using the Q4_X on 8 RTX 3090
🚀 1
12
#7 opened 2 months ago
by
martossien