Training-free MLA / GLA retrofits of Qwen3.8-27B with a 2x smaller KV cache. Weights preview; vLLM plugin, quants and code coming early October 2026.
TelperionAI
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ-gdn4
Image-Text-to-Text • 7B • Updated • 11.8k • 6 -
TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ
Image-Text-to-Text • 8B • Updated • 13k • 4 -
TelperionAI/Qwen3.8-27B-NVFP4-AWQ-AutoRound
Image-Text-to-Text • 20B • Updated • 326 • 7 -
TelperionAI/Qwen3.8-27B-FP8-block-AWQ
28B • Updated • 199 • 1
Training-free MLA / GLA retrofits of Qwen3.8-27B with a 2x smaller KV cache. Weights preview; vLLM plugin, quants and code coming early October 2026.
-
TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ-gdn4
Image-Text-to-Text • 7B • Updated • 11.8k • 6 -
TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ
Image-Text-to-Text • 8B • Updated • 13k • 4 -
TelperionAI/Qwen3.8-27B-NVFP4-AWQ-AutoRound
Image-Text-to-Text • 20B • Updated • 326 • 7 -
TelperionAI/Qwen3.8-27B-FP8-block-AWQ
28B • Updated • 199 • 1