Open-weight model · Image and text to text
MiniMax-M3.1-Flash-oQ4e-mtp
by MLX Community mlx-community/MiniMax-M3.1-Flash-oQ4e-mtp
MiniMax-M3.1-Flash-oQ4e-mtp is an open-weight model for image and text to text from MLX Community, released under other. It has 427.1B parameters. At 16-bit it needs about 1024.9 GB of GPU memory, which fits on 5x MI325X from $10.00 an hour; at 4-bit, 256.2 GB on 1x MI355X from $2.59, at the lowest prices in the SAVRN Index.
Parameters427.1B
Context—
Weights—
Licenseother
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve MiniMax-M3.1-Flash-oQ4e-mtp (427.1B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 854.1 GB | 1024.9 GB | 5x MI325X (256 GB) Vultr |
$10.00 | 4x MI355X $10.36 · 6x MI300X $11.10 |
| 8-bit | 427.1 GB | 512.5 GB | 2x MI355X (288 GB) Vultr |
$5.18 | 3x MI300X $5.55 · 3x MI325X $6.00 |
| 4-bit | 213.5 GB | 256.2 GB | 1x MI355X (288 GB) Vultr |
$2.59 | 2x MI300X $3.70 · 2x MI325X $4.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 23, 2026.
MiniMax-M3.1-Flash-oQ4e-mtp on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- mlx-community/MiniMax-M3.1-Flash-oQ4e-mtp
- Publisher
- MLX Community
- Task
- Image and text to text
- Modality
- Image and text
- Library
- mlx
- Parameters
- 427.1B parameters
- Languages
- mlx, oq, mtp
- Revision
- b377c2da4660d8c8be8348907fe4d5fe10af207d
- First published
- 2026-10-23
- Last updated
- 2026-10-23
License and Download
- License
- other
- Access
- Open weights, no gate
Download from MLX Community
Released by MLX Community through its official repository on Hugging Face.
Built From
- Derived from MiniMaxAI/MiniMax-M3.1-Flash
- Quantized from MiniMaxAI/MiniMax-M3.1-Flash
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 854.1 GB |
| 8-bit | 427.1 GB |
| 4-bit | 213.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About MiniMax-M3.1-Flash-oQ4e-mtp
How much GPU memory does MiniMax-M3.1-Flash-oQ4e-mtp need?
About 1024.9 GB at 16-bit and 256.2 GB at 4-bit: the weights (427.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run MiniMax-M3.1-Flash-oQ4e-mtp on?
At 16-bit, 5x MI325X from $10.00 an hour; at 4-bit, 1x MI355X from $2.59 an hour, at the lowest on-demand prices the SAVRN Index lists.
What license is MiniMax-M3.1-Flash-oQ4e-mtp released under?
other, as its publisher declares it. Read the license text before commercial use.
Similar Models
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. MathVision：our model’s score is…
A lossless repack of stepfun-ai/Step-5-Preview-NVFP4 (revision bc246cc2848e17b37f377eda8fd825c5b3018d1f), 17.1 GB smaller. The NVFP4 block scales of the routed experts are stored in b12x's compressed scale format (CSF), the lossless format introduced with nvidia/Qwen3.8-Flash-Next-FP4-Local. Every FP4 weight byte and every other tensor is identical to StepFun's checkpoint, and every scale decodes to StepFun's exact bytes, so this checkpoint computes exactly what Step-5-Preview-NVFP4 computes. Step 5 Preview is StepFun AI's model: a sparse mixture of experts with 600B total and 27B active parameters, text and image input, up to 1M tokens of context. Model card: stepfun-ai/Step-5-Preview.…
Join our WeChat or Discord community. Check out the GLM-5.3-Flash blog and GLM-5 Technical report. Use GLM-5.3-Flash API services on Z.ai API Platform. We introduce GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks. GLM-5.3-Flash starts from a newly trained base model, with its architecture and training recipe redesigned around capability and efficiency. For the first time in the GLM series, we introduce a hybrid architecture combining sparse and linear…