unsloth/Qwen3.8-27B-GGUF
27B • Updated • 9.06M • 3.3k
artden
artden111
·
AI & ML interests
None yet
Recent Activity
new activity 4 days ago
Qwen/Qwen3.8-27B:llama.cpp supports DFLash2 now new activity 12 days ago
Qwen/Qwen3.8-27B:DFlash2 speeds Qwen 3.8 27B up to 4 times new activity 12 days ago
unsloth/Qwen3.8-27B-GGUF:Introducing Unsloth Dynamic v3 Qwen3.8Organizations
None yet
llama.cpp supports DFLash2 now
1
#181 opened 4 days ago
by artden111
DFlash2 speeds Qwen 3.8 27B up to 4 times
1
#151 opened 12 days ago
by artden111
Introducing Unsloth Dynamic v3 Qwen3.8
👍🔥 52
34
#74 opened 13 days ago
by 
danielhanchen
What is mtp-Qwen3.8-27B-Q4_0.gguf used for?
2
#78 opened 13 days ago
by artden111
`Qwen3.8-27B-UD-IQ1_S.gguf`Has anyone tried this?
7
#76 opened 13 days ago
by artden111
Qwen3.8-27B: Q5_K_M, RTX 5060ti 16gb x 2, total 32gb, 30t/s, 215k context
🤗 1
15
#72 opened 14 days ago
by 
Artem7799
DFlash draft model instead of MTP one
👍 2
9
#54 opened 17 days ago
by artden111
liked 2
models 18 days ago
Qwen3.8-27B-Q4_0-qat possible?
🤝 2
2
#47 opened 18 days ago
by artden111
`preserve_thinking` for llama.cpp
1
#39 opened 18 days ago
by artden111
What does plus mean in "Context length 131,072+"?
➕ 2
7
#22 opened 22 days ago
by artden111
liked 2
models 21 days ago
Works well, comparable to Qwen 3.6 27B and then some
👀👍 2
4
#36 opened 21 days ago
by 
Omnomynous
What does plus mean in "Context length 131,072+"?
➕ 2
7
#22 opened 22 days ago
by artden111
What does plus mean in "Context length 131,072+"?
➕ 2
7
#22 opened 22 days ago
by artden111