estimate, except measured file sizes

Can I run Qwen3.6-35B-A3B locally?

35.95B total, 3B active. Parameter count is an estimate.

Licence:

Apache-2.0 source

Context:

262,144 tokens

Modality:

text + image/video in, text out

Released:

not recorded

Mixture-of-experts vision-language model, Apache-2.0. The card says 35B in total and 3B activated. Hugging Face safetensors metadata lists 35,951,822,704 parameters, all BF16. 35.95B is that count to two decimals, and 3B active is the card's round figure, so paramsEstimated stays true. VRAM math uses the total. 256 experts, 8 routed per token in the config. The card adds 1 shared expert. 40 layers: 30 linear_attention (Gated DeltaNet) and 10 full_attention (Gated Attention). 16 query heads, 2 KV heads, head dim 256. Linear-attention layers are stored with a sliding window of 0 so this formula gives them no token KV. The KV figure uses only the 10 full-attention layers and is an FP16 estimate. Config max_position_embeddings is 262,144. The card says that window is extensible to 1,010,000 tokens; this catalog uses 262,144. The card's citation is April 2026. Hugging Face lists the repo as created on 15 April 2026. Speed is not estimated: the formula streams every weight and understates sparse MoE, and no speed figure is stored. Unsloth GGUF sizes, decimal GB, checked 19 Oct 2026: UD-Q3_K_XL 16.85, UD-IQ4_XS 17.73, MXFP4_MOE 21.71, UD-Q4_K_M 22.13, UD-Q4_K_XL 22.36, Q8_0 36.90. Q8_0 is 36,903,140,320 bytes. mmproj-F16 is 0.90 GB (899,283,680 bytes) and is not a row in the memory table.

Parameter source · Architecture source · Model page

speed: not estimated for MoE yet

Memory per quant

KV is at 8,192 tokens. Overhead is 0.8 GB. Both are estimates. A measured file size is labelled. The last column is the cheapest machine that fits the total fully.

Cheapest rig that fits

UD-Q4_K_M, full: GeForce RTX 3090 24GB, €1,224 (used (median of sold listings))

UD-Q4_K_M, slow, partly in system RAM: Budget PC with RTX 3060 12GB, slow, partly in system RAM, €1,357 (estimate)

UD-Q3_K_XL (smallest file), full: GeForce RTX 3090 24GB, €1,224 (used (median of sold listings))

UD-Q3_K_XL (smallest file), slow, partly in system RAM: Budget PC with RTX 3060 12GB, slow, partly in system RAM, €1,357 (estimate)

Prices moved: see Building a local LLM rig in the RAMageddon.

On a specific GPU

• Qwen3.6-35B-A3B on RTX 3060 12GB
• Qwen3.6-35B-A3B on RTX 4060 Ti 16GB
• Qwen3.6-35B-A3B on RTX 3090
• Qwen3.6-35B-A3B on RTX 4090
• Qwen3.6-35B-A3B on RTX 5080
• Qwen3.6-35B-A3B on RTX 5090
• Qwen3.6-35B-A3B on RX 7900 XTX
• Qwen3.6-35B-A3B on Dual RTX 3090
• Qwen3.6-35B-A3B on Dual RTX 4090