Rent a GPU

Qwen3 Coder Next 80B-A3B hardware requirements

79.7B parameters (3B active, mixture of experts). Needs about 49.1 GB at Q4_K_M with 8K context.

Parameters80B3B active (MoE)
Q4_K_M · 8K49.1 GBthe usual download
FP16 · 8K160.2 GBfull precision
Runs well on4/51GPUs and Macs we track

Memory needed at each quantization

Weights, KV cache and runtime overhead, at 8K and 32K tokens of context.

QuantQuality8K context32K context
FP16Full quality160.2 GB160.8 GB
Q8_0Near-lossless85.5 GB86.1 GB
Q6_KExcellent66.2 GB66.8 GB
Q5_K_MVery good57.5 GB58.1 GB
Q4_K_MGood, most popular49.1 GB49.7 GB
Q3_K_MNoticeably degraded39.8 GB40.4 GB
Q2_KHeavily degraded30.7 GB31.3 GB

Run it with Ollama

Downloads Q4_K_M by default.

ollama run qwen3-coder-next

Model card

Qwen/Qwen3-Coder-Next on Hugging Face: licence, prompt format and GGUF builds.

Run it in the cloud

Run Qwen3 Coder Next 80B-A3B on a rented GPU today.

It needs about 49.1 GB at Q4_K_M: a rented A100 / H100 80 GB runs it for about $1.11 to $3.99 an hour.

RunPodRent a GPU on RunPodVast.aiRent a GPU on Vast.ai

Every GPU and Mac checked

Sorted by memory. Bars show how much of each card Qwen3 Coder Next 80B-A3B fills at the best quant that fits.

4 Runs well

NameMemory usedBest quantSpeed

6 Fits with heavy quantization

NameMemory usedBest quantSpeed

41 Too big

NameMemory usedBest quantSpeed

Other Qwen models