One Model to Rule Them All: Qwen3.5 122B on a Homelab for CF Agents | CF Weekly #85
One Model to Rule Them All: Qwen3.5 122B on a…
You don’t need the cloud. You need four RTX 3090s and a dream. This week on CF Weekly we deploy Qwen3.5-122B-A10B — 122 billion parameters, 10B active per token, 262K native context — directly on homelab hardware using vLLM. We cover the GPTQ Int4 quantization gotchas, the […]
Hinterlasse einen Kommentar