What GPU do I need to run Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8?
480.2B parameters, published in F8_E4M3. View on Hugging Face
Set up Qwen3-Coder…35B-Instruct-FP8Qwen3-Coder-480B-A35B-Instruct-FP8 is published by Qwen on Hugging Face, with 431,010 downloads and 159 likes to date. It's a Qwen3MoeForCausalLM model built for text-generation, published natively in F8_E4M3.
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-Coder-480B-A35B-Instruct-FP8 at its published (F8_E4M3) precision: 3× AMD MI300X on runpod, at $2.39/hr per GPU ($7.17/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Qwen3-Coder-480B-A35B-Instruct-FP8: common questions
Can Qwen3-Coder-480B-A35B-Instruct-FP8 run on a single GPU?
No. At FP8 (native) it needs 536.6 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 192.0 GB AMD MI300X, and it takes 3 of them.
Is Qwen3-Coder-480B-A35B-Instruct-FP8 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 536.6 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 268.3 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
How many GPUs do I need to run Qwen3-Coder-480B-A35B-Instruct-FP8?
3 at FP8 (native). It needs 536.6 GB of VRAM and the cheapest capable live offer is a 192.0 GB AMD MI300X on runpod, so 3 of them come to $7.17/hr in total.
Does quantizing Qwen3-Coder-480B-A35B-Instruct-FP8 lower the GPU bill?
Yes. At FP8 (native) the cheapest live fit is 3 AMD MI300X cards on runpod at $7.17/hr. At INT4 (quantized) it drops to 6 RTX 8000 cards on akash at $1.32/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Qwen models
- Qwen3-0.6B (752M, BF16)
- Qwen3-8B (8.2B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
- Qwen3.5-9B (9.7B, BF16)
- Qwen2.5-7B-Instruct (7.6B, BF16)
- Qwen3-VL-8B-Instruct (8.8B, BF16)
