Qwen3-Coder-Next needs about 80 GB of GPU memory for FP8 weights. The smallest fitting setup at 32k context is 1× NVIDIA B200. It supports 64 concurrent conversations with SGLang defaults.
GPU requirements by context length
8k context
GPU
GPUs
Concurrent users
NVIDIA B200
1
64
NVIDIA H200 SXM
1
64
NVIDIA H100 NVL
1
9
NVIDIA RTX PRO 6000 Blackwell Server Edition
1
14
NVIDIA H20
1
14
NVIDIA H100 SXM
2
64
NVIDIA A100 80GB SXM
2
64
NVIDIA L40S
4
64
32k context
GPU
GPUs
Concurrent users
NVIDIA B200
1
64
NVIDIA H200 SXM
1
41
NVIDIA H100 NVL
1
3
NVIDIA RTX PRO 6000 Blackwell Server Edition
1
5
NVIDIA H20
1
5
NVIDIA H100 SXM
2
64
NVIDIA A100 80GB SXM
2
56
NVIDIA L40S
4
44
128k context
GPU
GPUs
Concurrent users
NVIDIA B200
1
24
NVIDIA H200 SXM
1
11
NVIDIA H100 NVL
1
0
NVIDIA RTX PRO 6000 Blackwell Server Edition
1
1
NVIDIA H20
1
1
NVIDIA H100 SXM
2
19
NVIDIA A100 80GB SXM
2
16
NVIDIA L40S
4
12
FP8 weights, SGLang defaults, estimates.
Weights by precision
Weight memory
Precision
Weights
Smallest fitting setup at 32k
BF16
about 159 GB
1x NVIDIA B200
FP8
about 80 GB
1x NVIDIA B200
INT4 (AWQ)
about 44 GB
1x NVIDIA B200
Model notes
Attention
Hybrid attention, full + sliding-window layers
Architecture
Mixture-of-Experts
Layers
48
Hidden size
2,048
Vocabulary
151,936
Native precision
bfloat16
At 32k context, 26% of this card's usable memory is working as conversation cache.
Frequently asked questions
Will Qwen/Qwen3-Coder-Next run on a single H100?
No, a single H100 SXM cannot hold Qwen/Qwen3-Coder-Next at 32k context with FP8 weights. The model requires multiple GPUs.
What is the cheapest GPU setup for Qwen/Qwen3-Coder-Next?
The cheapest fitting setup at 32k context is 1x NVIDIA B200 with FP8 weights and SGLang defaults.
How much VRAM does Qwen/Qwen3-Coder-Next need at 128k context?
At 128k context on the cheapest fitting setup, Qwen/Qwen3-Coder-Next uses about 80 GB of VRAM per GPU for FP8 weights and about 1.7 GB per conversation for the KV cache. The total VRAM needed depends on the GPU count and parallelism configuration.
Can I run Qwen/Qwen3-Coder-Next with INT4 quantization?
Yes, Qwen/Qwen3-Coder-Next has INT4 weight figures. Its weights take about 44 GB in INT4 versus about 80 GB in FP8. INT4 can make the model fit on fewer GPUs, but check inference quality for your workload.
Want a different context length, GPU, or quantization? The calculator runs the same numbers live, preloaded with this model.