MiniMax M3.1 Flash 428B-A23B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
MiniMax's October refresh of M3 for coding, agents, computer use and cybersecurity: the same 428B-total, 23B-active multimodal MoE (text, image and video in, 1M-token context) with sparse attention throughout, quantisation-aware training and speculative decoding. The native checkpoint keeps its experts in NVFP4, so it downloads at 252 GB instead of M3's full-precision size. Datacentre-scale to self-host.
MiniMax M3.1 Flash 428B-A23B needs about 259 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 141.5 GB | — | Too big | |
| Q3_K_M 3.41 bpw | 183.2 GB | — | Too big | |
| Q4_K_M 4.83 bpw | 259.2 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 304.1 GB | — | Too big | |
| Q6_K 6.56 bpw | 351.8 GB | — | Too big | |
| Q8_0 8.50 bpw | 455.6 GB | — | Too big | |
| F16 16.00 bpw | 856.8 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. MiniMax M3.1 Flash 428B-A23B VRAM calculator →
Get MiniMax M3.1 Flash 428B-A23B running
The cheapest catalogued GPU that runs MiniMax M3.1 Flash 428B-A23B is the Apple M3 Ultra (512 GB).
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run MiniMax M3.1 Flash 428B-A23B
No Ollama tag for M3.1 Flash on 2026-10-25.
Specifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 428 Billion (23B active)
- Context window
- 1M
- Architecture
- Mixture-of-Experts (multimodal), MiniMax Sparse Attention
- Provider
- MiniMax
- Licence
- MiniMax Community License
- Availability
- Weights downloadable
- Practical deployment
- Workstation (large unified memory or pro GPU)
- Specified at
- Q4_K_M
- System RAM
- 512 GB
- Record updated
- 2026-10-25
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Limits and caveats
- The 252 GB figure is MiniMax's own NVFP4/MXFP8 download (summed from the Hugging Face file listing). The Q4_K_M figure on this page is sized from the parameter count, as for any GGUF build; the two are different files.
- No KV-cache figure: MiniMax Sparse Attention is not modelled here, so the per-quant table is sized at zero context.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run MiniMax M3.1 Flash 428B-A23B on my GPU?
- MiniMax M3 on AMD Ryzen AI Max+ 395
- MiniMax M3 on Apple M1 Max
- MiniMax M3 on Apple M1 Ultra
- MiniMax M3 on Apple M2 Max
- MiniMax M3 on Apple M2 Ultra
- MiniMax M3 on Apple M3 Max
- MiniMax M3 on Apple M4 Max
- MiniMax M3 on Apple M5 Max
- MiniMax M3 on Apple M5 Pro
- MiniMax M3 on NVIDIA A100 80GB (PCIe)
- MiniMax M3 on NVIDIA DGX Spark
- MiniMax M3 on NVIDIA H100 80GB (PCIe)
- MiniMax M3 on NVIDIA RTX PRO 6000 Blackwell
Other MiniMax M3 sizes
MiniMax M3.1 Flash 428B-A23B — frequently asked questions
How much VRAM does MiniMax M3.1 Flash 428B-A23B need?
About 259 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does MiniMax M3.1 Flash 428B-A23B run on an RTX 4090 (24 GB)?
No. MiniMax M3.1 Flash 428B-A23B needs about 259 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run MiniMax M3.1 Flash 428B-A23B locally?
No Ollama tag for M3.1 Flash on 2026-10-25. Running the published tag would send your prompts to a hosted GPU rather than your own machine.
What other sizes does MiniMax M3 come in?
MiniMax M3 428B-A23B (259 GB), MiniMax M3-VL (140 GB), MiniMax M3.1 Flash 428B-A23B (259 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.