MiniMax-M1-40k Memory at each precision, the licence in plain words, and where it fits.
Short answer. MiniMax-M1-40k needs about 261 GB of memory at 4-bit, 489 GB at 8-bit and 916 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 456.1 billion parameters. Licence in short: commercial use allowed. 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-M1-40k is a language model for chat, drafting and question answering, published by MiniMax on Hugging Face on 5 June 2025. It has about 456.1 billion parameters. It is a mixture-of-experts model: 32 experts, 2 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 20,602 downloads of it in the 30 days before we checked (7 Oct 2026), and 185 people have liked it there.
02
How much memory it needs
How these figures are worked out: weights = parameters × bits per weight ÷ 8. The KV cache is added for 8,192 tokens of context, plus about 1.5 GB of runtime overhead. Treat the totals as planning estimates.
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)
912 GB
2.7 GB
916 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
MiniMaxM1ForCausalLM
Model type
minimax_m1
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
10,240,000
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
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
Llama-3.1-405B-Instruct (405.9B parameters, about 230 GB at 4-bit before context; commercial use allowed, with conditions)
Nemotron-3-Ultra-550B-A55B (560.5B parameters, about 317 GB at 4-bit before context; custom licence: check before commercial use)
GLM-4.5 (358.3B parameters, about 203 GB at 4-bit before context; commercial use allowed)
07
Questions people ask
How much memory does MiniMax-M1-40k need?
About 261 GB at 4-bit, 489 GB at 8-bit and 916 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-M1-40k 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-M1-40k 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.
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.
