sharky172/ qwen3.6:35b-a3b-mtp-q4_K_M-512k

851 2 weeks ago

Qwen 3.6, MTP-enabled, 512k context (20GB KV cache footprint with OLLAMA_KV_CACHE_TYPE=q8_0)

ollama run sharky172/qwen3.6:35b-a3b-mtp-q4_K_M-512k

Details

2 weeks ago

6d5c30344cc0 · 22GB ·

qwen35moe
·
35.5B
·
Q4_K_M
{ "num_ctx": 524288 }

Readme

No readme