Qwen3-Coder-Next The memory it needs, what you may do with it, and the hardware it suits.
Short answer. Qwen3-Coder-Next needs about 47 GB of memory at 4-bit, 87 GB at 8-bit and 162 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 79.7 billion parameters and a 262,144-token context window. Licence in short: commercial use allowed. By memory alone, on ANVE’s launch configurations: ANVE One fits at 4-bit, ANVE Office only with partial offload to system memory, which is much slower, ANVE Office Pro (GPU) only with partial offload to system memory, which is much slower. These are estimates from its published size, not benchmarks.
01
What it is
Qwen3-Coder-Next is a language model for chat, drafting and question answering, published by Alibaba’s Qwen team on Hugging Face on 30 January 2026. It has about 79.7 billion parameters and a configured context window of 262,144 tokens. It is a mixture-of-experts model: 512 experts, 10 used for each token.
Its card lists the licence as Apache 2.0. In short, the licence allows commercial use, modification and redistribution, with attribution and a copy of the licence, and includes a patent grant.
Hugging Face counted about 600,307 downloads of it in the 30 days before we checked (7 Oct 2026), and 1,678 people have liked it there.
02
How much memory it needs
The arithmetic: parameters × bits per weight ÷ 8 gives the weights; add the KV cache, which grows with every token of context; then add about 1.5 GB for the runtime. These are estimates for planning, not measurements.
Each token of context adds about 0.10 MB of KV cache at 16-bit, so 32,768 tokens would add about 3.2 GB.
Precision
Weights
KV cache (8,192 tokens)
Total, estimated
BF16 (full precision)
159 GB
0.81 GB
162 GB
8-bit (Q8_0)
85 GB
0.81 GB
87 GB
4-bit (Q4_K)
45 GB
0.81 GB
47 GB
03
Architecture at a glance
Setting
Value in config.json
Architecture class
Qwen3NextForCausalLM
Model type
qwen3_next
Layers
48
Hidden size
2,048
Attention heads
16
Key-value heads
2 (grouped-query attention)
Head size
256
Vocabulary
151,936
Experts
512, 10 active per token
Configured context
262,144
Stored precision
bfloat16
04
Will it fit on ANVE?
Arithmetic against the launch specification, not a test: about three quarters of ANVE One’s 64 GB of unified memory for the model (as AMD’s Variable Graphics Memory allows), and the 24 GB on the graphics card in ANVE Office and ANVE Office Pro, which keep the rest of the stack in 64 GB and 128 GB of system memory. ANVE’s tested default is Qwen 3.8 27B; this model is not yet validated on ANVE.
Configuration (at launch)
Memory for the model
Verdict
ANVE One
about 48 GB of 64 GB unified memory
fits at 4-bit
ANVE Office
24 GB on the RTX PRO 4000 Blackwell SFF Edition
only with partial offload to system memory, which is much slower
ANVE Office Pro (GPU)
24 GB on the RTX PRO 4000 Blackwell
only with partial offload to system memory, which is much slower
05
What an office would use it for
Models this large are stronger on long, hard drafting and reasoning, but need most of a 64 to 128 GB machine even at 4-bit, which leaves less room for long documents and several users.
06
Similar models to compare
Hunyuan-A13B-Instruct (80.4B parameters, about 47 GB at 4-bit before context; custom licence: check before commercial use)
Apertus-70B-2509 (70.6B parameters, about 41 GB at 4-bit before context; commercial use allowed)
DeepSeek-R1-Distill-Llama-70B (70.6B parameters, about 41 GB at 4-bit before context; commercial use allowed)
07
Questions people ask
How much memory does Qwen3-Coder-Next need?
About 47 GB at 4-bit, 87 GB at 8-bit and 162 GB at full 16-bit precision, including an 8,192-token KV cache and about 1.5 GB of runtime overhead. These are estimates from its parameter count.
Can Qwen3-Coder-Next run on a 24 GB graphics card?
Not entirely: even at 4-bit it needs about 47 GB, so part of it would sit in system memory, which is much slower.
Is Qwen3-Coder-Next free for commercial use?
Its card lists Apache 2.0, which allows commercial use, modification and redistribution, with attribution and a copy of the licence, and includes a patent grant. Read the licence itself before relying on this summary; it is not legal advice.
What is Qwen3-Coder-Next’s context window?
Its configuration sets 262,144 tokens. Longer contexts need more memory for the KV cache, so the practical limit on a given machine can be lower.
08
What is not real yet
No sealed ANVE unit exists; every image of the appliance on this site is a labelled render. The software runs today on a development machine. No customers yet, no certifications, no delivery date, and the final price is not announced.
Reservations are ₹999 in India or US$12 elsewhere, refundable in full until you confirm an order in writing (terms). Offices that cannot use cloud AI can apply to be one of ten design partners.
