MiniMax-VL-01 How much memory it needs, what its licence allows, and whether it fits an office box.
Short answer. MiniMax-VL-01 needs about 261 GB of memory at 4-bit, 489 GB at 8-bit and 917 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 456.4 billion parameters and an 8,192-token context window. Licence in short: licence not stated. By memory alone, on ANVE’s launch configurations: ANVE One does not fit, ANVE Office does not fit, ANVE Office Pro (GPU) does not fit. These are estimates from its published size, not benchmarks.
01
What it is
MiniMax-VL-01 is a vision-language model: it reads images (scanned pages, photos, charts and screenshots) as well as text, published by MiniMax on Hugging Face on 12 January 2025. It has about 456.4 billion parameters and a configured context window of 8,192 tokens. It is a mixture-of-experts model: 32 experts, 2 used for each token.
Its card lists the licence as no licence stated on the model card. In short, the licence does not state its terms on the card; ask the publisher before any use.
Hugging Face counted about 30,339 downloads of it in the 30 days before we checked (7 Oct 2026), and 286 people have liked it there.
02
How much memory it needs
We size it the way you would size any model: the weights (parameters × bits ÷ 8), the KV cache for 8,192 tokens of context, and roughly 1.5 GB for the runtime itself. Real use varies with settings.
Each token of context adds about 0.33 MB of KV cache at 16-bit, so 32,768 tokens would add about 11 GB.
Precision
Weights
KV cache (8,192 tokens)
Total, estimated
BF16 (full precision)
913 GB
2.7 GB
917 GB
8-bit (Q8_0)
485 GB
2.7 GB
489 GB
4-bit (Q4_K)
257 GB
2.7 GB
261 GB
03
Architecture at a glance
Setting
Value in config.json
Architecture class
MiniMaxVL01ForConditionalGeneration
Model type
minimax_vl_01
Layers
80
Hidden size
6,144
Attention heads
64
Key-value heads
8 (grouped-query attention)
Head size
128
Vocabulary
200,064
Experts
32, 2 active per token
Configured context
8,192
04
Will it fit on ANVE?
How the verdicts are worked out: on ANVE One, about three quarters of 64 GB of unified memory is available to the model; on ANVE Office and ANVE Office Pro, the model has to fit in the 24 GB on the graphics card, with 64 GB or 128 GB of system memory for everything else. This is arithmetic against the launch specification, not a test. 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
does not fit
ANVE Office
24 GB on the RTX PRO 4000 Blackwell SFF Edition
does not fit
ANVE Office Pro (GPU)
24 GB on the RTX PRO 4000 Blackwell
does not fit
05
What an office would use it for
This is frontier-scale: even at 4-bit it needs far more memory than any single office box, so it belongs on a multi-GPU server or a cloud service, not on an appliance.
06
Similar models to compare
Qwen3.5-397B-A17B (403.4B parameters, about 228 GB at 4-bit before context; commercial use allowed)
GLM-5.3-Flash (321.3B parameters, about 182 GB at 4-bit before context; commercial use allowed)
DeepSeek-V4.1-Flash (763.2B parameters, about 431 GB at 4-bit before context; commercial use allowed)
07
Questions people ask
How much memory does MiniMax-VL-01 need?
About 261 GB at 4-bit, 489 GB at 8-bit and 917 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 MiniMax-VL-01 run on a 24 GB graphics card?
Not entirely: even at 4-bit it needs about 261 GB, so part of it would sit in system memory, which is much slower.
Is MiniMax-VL-01 free for commercial use?
Its card lists no licence stated on the model card, which does not state its terms on the card; ask the publisher before any use. Read the licence itself before relying on this summary; it is not legal advice.
What is MiniMax-VL-01’s context window?
Its configuration sets 8,192 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.
