qwen3.6

3 articles · newest first

Editorial infographic of a solid dense 27B model block fitting neatly inside a 24GB graphics card, near-black background, indigo-violet with a coral accent

Qwen3.6 27B locally: the all-dense 24GB Qwen

Qwen3.6's dense 27B is the no-fuss 24GB-card option — every parameter fires, nothing to offload, a real 256K context. The VRAM math, the GPU, and how it differs from the 35B-A3B MoE.

Lena Fischer · 2h ago · 7 min

Isometric diorama of a grid of many small expert blocks with only a few lit up feeding a token, near-black background, indigo-violet with a coral accent

Qwen3.6 35B-A3B locally: a 35B that thinks like a 3B

Qwen3.6's default is a mixture-of-experts model: 35B on disk, 3B active per token. That makes it fast — but the VRAM math has a twist worth understanding before you buy a card.

Lena Fischer · 2h ago · 7 min

Flat illustration of a person choosing between small, medium and large boxes to fit into a slot on a graphics card, a small robot helper watching

Agents

Run OpenClaw or Hermes on a local model: which fits your GPU

Ollama's default gemma4 is the small E4B and qwen3.5 is the 9B, not what most people assume. What each tag really downloads, what the bigger models need at the 64K context agents use, and what to pick for 12, 16 and 24GB cards.

Lena Fischer · 23h ago · 7 min