sharky172/ qwen3.6:35b-a3b-mtp-q8_0-512k

819 1 week ago

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

... /
params
1217b8c3d63f · 19B
{
"num_ctx": 524288
}