Vladimir
vstiff
AI & ML interests
None yet
Recent Activity
liked a model 2 days ago
agentionai/Qwen3.8-Flash-Next-MTP-Q8_0-GGUF new activity 2 days ago
agentionai/Signal-3.8-Flash-Next-GGUF:Looks great liked a model 3 days ago
agentionai/Signal-3.8-Flash-Next-GGUFOrganizations
None yet
Looks great
❤️ 1
#4 opened 2 days ago
by
vstiff
Introducing Qwen3.8-Flash Unsloth Dynamic v3.1 GGUFs!
❤️🚀 21
20
#91 opened 16 days ago
by
danielhanchen
Qwen3.8-Flash-Next-GGUF Unsloth Dynamic 3.0 Quants
👍 4
4
#88 opened 20 days ago
by
Vinyl86
Unsloth taking shots at ISTA
🔥👀 12
18
#29 opened 21 days ago
by
spanspek
Q2_0 randomly generates Chinese tokens during English responses
8
#60 opened 28 days ago
by
sleepynlp
MTP model?
2
#2 opened about 1 month ago
by
LaurentPayot
Does it still hallucinate?
🔥❤️ 3
6
#4 opened about 2 months ago
by
vstiff
Q4_K_XL / llama-server / Hallucination after 150k of filled context
3
#42 opened 3 months ago
by
manisab
Identified serious issue with Flash-Next hallucinating user instructions!
1
#57 opened 2 months ago
by
laserbeans
strix halo 128gb recommendations
21
#28 opened 3 months ago
by
dilavni
Qwen3.8-Flash-Next on Strix Halo: ~40 tok/s code at 120K+ context
👍 9
4
#45 opened 3 months ago
by
Engardium
rocm support
3
#1 opened 3 months ago
by
idchrono
Love your models, any chance of something between 35b and 397b?
👍 5
4
#1 opened 3 months ago
by
Shaunm89
Ryzen AI Max+ 395 results: 16.68 tok/s with UD-Q5_K_XL, Vulkan and MTP 4
❤️ 3
12
#41 opened 3 months ago
by
erstmalreden
I think this model is not ready for use
👀👍 7
20
#40 opened 3 months ago
by
sa13ma
Same tool call infinite loop
1
#139 opened 4 months ago
by
vstiff
1-bit Kimi K3 vs Claude Opus 5 vs GPT 5.6
👀🚀 21
25
#12 opened 4 months ago
by
danielhanchen
Wrong Qwen3.6-35B-A3B Benchmark
👍 1
2
#17 opened 4 months ago
by
XCurOS-35H