Run Qwen3-Coder-Next locally: hardware requirements
Qwen3-Coder-Next needs about 156 GB of GPU memory for one person at 32K context, and about 1.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 179 GB, which takes 2 × RTX PRO 6000 Blackwell.
Alibaba (Qwen), China. From its files on Hugging Face, checked 2026-11-05.
Context per person: more context lets the model work with longer conversations and more files, and needs more GPU memory for every person. As a guide: 8K for short chat, 32K for chat over documents, 64K for AI agents, whose instructions, tools and files all count.
80 users means about 16 people working at the same moment. That share is a planning assumption; if you know yours, choose the total that matches it.
Work it out for your team: Qwen/Qwen3-Coder-Next
On Hugging FaceAlibaba (Qwen), China · 80B parameters · License: apache-2.0
What you need for 16 active users
2 × RTX PRO 6000 Blackwell
It holds the model and up to 18 active users at 64K context.
The server
384 GB RAM
48 CPU cores
1 TB NVMe
Rules of thumb
- GPU memory in total
- 179 GB
- Weights
- 159 GB (published files)
- Conversation cache, all active
- 24.0 GB
- Engine (vLLM)
- 3.0 GB
Ways to need less
- Use 32K context per person1 × B200
- Use 8K context per person1 × B200
- Use a 4-bit build1 × A100
- Use a smaller model: Qwen3.6-35B-A3B1 × H200 NVL
- Use a smaller model: Qwen3.8-27B1 × H200 NVL
Your options by card
80 users means about 16 using the model at any moment. The others are not waiting; they are simply doing something else. If more become active than a build handles, they queue. 9 cards too small for this model are left out.
| Card | Memory | Active users, one server | For your 16 active |
|---|---|---|---|
| A100 | 80 GB | 49 | 3 × A100 |
| B200 | 180 GB | 125 | 2 × B200 |
| H100 | 80 GB | 49 | 3 × H100 |
| H200 NVL | 141 GB | 75 | 2 × H200 NVL |
| L40S | 48 GB | 18 | 4 × L40S |
| RTX 6000 Ada | 48 GB | 18 | 4 × RTX 6000 Ada |
| RTX PRO 5000 Blackwell | 48 GB | 18 | 4 × RTX PRO 5000 Blackwell |
| RTX PRO 6000 Blackwell | 96 GB | 18 | 2 × RTX PRO 6000 Blackwell |
These are memory limits. A card can hold more people than it can answer quickly, so test your own workload before you buy. More than one card in a server needs an engine that splits the model.
Qwen3-Coder-Next by team size
AI agents, 1 user in 5 active at a time, 64K context, as published.
| Total users | At once | GPU memory | What you need |
|---|---|---|---|
| 20 | 4 | 161 GB | 1 × B200 |
| 80 | 16 | 179 GB | 2 × RTX PRO 6000 Blackwell |
| 120 | 24 | 191 GB | 2 × H200 NVL |
| 500 | 100 | 305 GB | 2 × B200 |
Similar models
- Qwen3.6-35B-A3BAlibaba (Qwen) · 36B · 91.3 GB for 16 at once
- Qwen3.8-Flash-NextAlibaba (Qwen) · 180B · 369 GB for 16 at once
- Qwen3.8-27BAlibaba (Qwen) · 28B · 120 GB for 16 at once
- Qwen3-14BAlibaba (Qwen) · 15B · 131 GB for 16 at once
- Qwen3.5-9BAlibaba (Qwen) · 9.7B · 53.3 GB for 16 at once
- Qwen3-VL-8B-InstructAlibaba (Qwen) · 8.8B · 164 GB for 16 at once
How this is worked out
GPU memory = weights + a conversation cache for each person + the serving engine, from this model's files on Hugging Face. These are memory limits, not speed. The full method and its limits.
Questions
How much GPU memory does Qwen3-Coder-Next need?
Qwen3-Coder-Next needs about 156 GB of GPU memory for one person at 32K context, and about 1.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 179 GB, which takes 2 × RTX PRO 6000 Blackwell.
How many active users can Qwen3-Coder-Next handle on one 96 GB GPU?
Qwen3-Coder-Next does not fit on one 96 GB card such as the RTX PRO 6000 Blackwell at 64K context. Compare larger cards or a smaller precision above.
Can Qwen3-Coder-Next run on a 24 GB GPU such as the RTX 4090?
Not as published for one person at 32K context: it needs about 156 GB. A 4-bit or 8-bit build may fit, if the model has one.
What license does Qwen3-Coder-Next use?
Hugging Face lists its license as apache-2.0. Check the license on the model's page before you use it.
Running a model on your own servers?
NeueCode is private autonomous intelligence for enterprise: it takes on your organization's tasks on your own GPUs, with nothing leaving your network, a person approving every action, and all of it on record. It runs each model on one card, so read the single-card figures above.
What you need to run NeueCode