What GPU do I need to run z-lab/Qwen3.6-35B-A3B-DFlash?
386M parameters, published in BF16. View on Hugging Face
Set up Qwen3.6-35B-A3B-DFlashQwen3.6-35B-A3B-DFlash is published by z-lab on Hugging Face, with 246,286 downloads and 289 likes to date. It's a DFlashDraftModel model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Qwen3.6-35B-A3B-DFlash at its published (BF16) precision: 1× A16 on vultr, at $0.059/hr per GPU ($0.059/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Qwen3.6-35B-A3B-DFlash: common questions
How much VRAM does Qwen3.6-35B-A3B-DFlash need?
0.9 GB at BF16, 0.4 GB at FP8 (quantized), 0.2 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 0.7 GB of weights plus inference overhead is the whole requirement.
How many copies of Qwen3.6-35B-A3B-DFlash fit on one A16?
2, by VRAM alone. That card carries 2.0 GB and one copy needs 0.9 GB at BF16, on a live rate of $0.059/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More z-lab models
- Qwen3.8-27B-DFlash2 (1.9B, BF16)
- Qwen3.6-27B-DFlash (1.7B, BF16)
- Qwen3.5-9B-DFlash (1.3B, BF16)
- Qwen3-8B-DFlash-b16 (1.0B, BF16)
- gemma-4-26B-A4B-it-DFlash (430M, BF16)
- gemma-4-31B-it-DFlash (1.5B, BF16)
