MiniMax · Chat and reasoning · 428B parameters · 23B active · MiniMax Community License
MiniMax-M3.1-Flash
Needs 301 GB at INT4 / MXFP4. The smallest real configuration today is 4× A100 80GB at Vast.ai, $2.40 per hour, about $1,754 a month at 730 hours.
Parameters428B23B active per token
Context1M tokensmaximum published
Checkpoint250 GBINT4-packed, as published
LicenseMiniMax Community Licensecheck before commercial use
ReleasedOct 23, 2026documented date
Smallest configuration · INT4 / MXFP4
4× A100 80GB320 GB VRAM · 94% used
- Per hour
- $2.40
- Per month
- $1,754
- Cheapest at
Vast.ai
What is documented about MiniMax-M3.1-Flash
news checked 2026-10-27Hosted launch 2026-10-19; weights 2026-10-23 (HF first commit and TechNode). Card: 'Approximately 428B total; 23B activated'; HF counts 220.5B because FP4 values are packed. Text, image and video input; context up to 1,000,000 tokens per the card. It keeps M3's MoE architecture, with MiniMax Sparse Attention in all layers, QAT, and a DSpark draft head (an extra 2.30 GB in dspark/). Download is about 3.4x smaller than M3 in BF16 (854 GB).
- https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash
- https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash/raw/main/config.json
- https://huggingface.co/api/models/MiniMaxAI/MiniMax-M3.1-Flash?blobs=true
Memory · 1 precision · 6 context lengthsHow much VRAM it needs
Weights plus runtime overhead, then the KV cache that grows with the context you serve.
| Precision | Weights | Weights + headroom | 4k context | 32k context | 128k context | 256k context | 1M context |
|---|---|---|---|---|---|---|---|
| INT4-packedpublished checkpoint | 250 GB | 301 GB | 301 GB | 305 GB | 317 GB | 333 GB | 429 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 5 GB | 17 GB | 33 GB | 129 GB |
Cross-checked on Hugging Face Oct 28, 2026: 220.5B parameters in the safetensors headers, 252.4 GB of weight files, attention layout from config.json (60 layers, 4 KV heads × 128). Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache = 2048 bytes per token per layer × 60 full-attention layers (FP16 cache, one sequence).config.json ↗
Smallest configuration per GPU · 110 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| A100 80GBBest fit | 4× 80 GB320 GB total | 94% tight | $2.40 | $1,754 | Vast.aiTrust 78 · read Nov 1 · receipt · also Spheron $4.76, Gcore $5.63 |
| A100 40GB | 8× 40 GB320 GB total | 94% tight | $3.20 | $2,338 | Vast.aiTrust 78 · read Nov 1 · receipt · also Edgevana $4.67, Denvr Cloud $9.20 |
| RTX A6000 | 8× 48 GB384 GB total | 78% | $3.36 | $2,453 |  LiumTrust 40 · read Nov 1 · receipt · also LeaderGPU $3.58, GPU.ai $3.76 |
| L40S | 8× 48 GB384 GB total | 78% | $3.74 | $2,727 | Vast.aiTrust 78 · read Nov 1 · receipt · also Lium $6.00, GPU.ai $6.40 |
| RTX PRO 6000 | 4× 96 GB384 GB total | 78% | $3.84 | $2,805 | Vast.aiTrust 78 · read Nov 1 · receipt · also UpCloud $3.89, Hetzner $6.44 |
| Gaudi 2 | 4× 96 GB384 GB total | 78% | $4.18 | $3,052 |  Cyfuture AInot scored · read Nov 1 · receipt |
| A40 | 8× 48 GB384 GB total | 78% | $4.61 | $3,364 |  LeaderGPUTrust 59 · read Nov 1 · receipt · also Exoscale $8.36 |
| A100X | 4× 80 GB320 GB total | 94% tight | $5.12 | $3,739 | Vast.aiTrust 78 · read Nov 1 · receipt |
| RTX 6000 Ada | 8× 48 GB384 GB total | 78% | $5.20 | $3,796 |  GPU.ainot scored · read Nov 1 · receipt · also io.net $5.46, QuantaCloud $6.21 |
| MI300X | 2× 192 GB384 GB total | 78% | $5.71 | $4,167 | Cyfuture AInot scored · read Nov 1 · receipt · also Hot Aisle $5.98, AtmosCompute $6.69 |
| MI325X | 2× 256 GB512 GB total | 59% | $6.21 | $4,536 | Cyfuture AInot scored · read Nov 1 · receipt |
| H100 | 4× 80 GB320 GB total | 94% tight | $6.84 | $4,991 |  GcoreTrust 80 · read Nov 1 · receipt · also Edgevana $7.98, UpCloud $8.00 |
| B200 | 2× 180 GB360 GB total | 83% | $8.22 | $6,002 |  UpCloudTrust 75 · read Nov 1 · receipt · also Deep Infra $9.78, Elice AI Cloud $13.64 |
| L40 | 8× 48 GB384 GB total | 78% | $8.40 | $6,132 |  OblivusTrust 82 · read Nov 1 · receipt · also CoreWeave $10.00, AtmosCompute $12.21 |
| RTX PRO 6000D | 4× 84 GB336 GB total | 89% | $10.56 | $7,709 | AtmosComputenot scored · read Nov 1 · receipt |
| H200 NVL | 4× 141 GB564 GB total | 53% | $10.67 | $7,788 | Vast.aiTrust 78 · read Nov 1 · receipt · also IONOS $13.04, Geodd $13.56 |
| H200 | 4× 141 GB564 GB total | 53% | $11.05 | $8,070 | Vast.aiTrust 78 · read Nov 1 · receipt · also Theta EdgeCloud $14.76, Canopy Wave $16.00 |
| B300 | 2× 288 GB576 GB total | 52% | $11.65 | $8,506 | UpCloudTrust 75 · read Nov 1 · receipt · also FPT AI Factory $13.98, Vast.ai $17.00 |
| H100 NVL | 4× 94 GB376 GB total | 80% | $12.48 | $9,112 | Vast.aiTrust 78 · read Nov 1 · receipt · also EmpirioLabs AI $22.40, Open Telekom Cloud $25.90 |
| B200 CC | 2× 180 GB360 GB total | 83% | $18.09 | $13,206 |  VerdaTrust 81 · read Nov 1 · receipt |
| MI355X | 8× 288 GB2304 GB total | 13% | $23.60 | $17,228 |  TensorWaveTrust 64 · read Nov 1 · receipt |
| GB300 | 2× 288 GB576 GB total | 52% | $26.11 | $19,060 | VerdaTrust 81 · read Nov 1 · receipt |
| B300 CC | 4× 288 GB1152 GB total | 26% | $46.31 | $33,806 | VerdaTrust 81 · read Nov 1 · receipt |
| A800 80GB PCIe | 8× 80 GB640 GB total | 47% | $50.80 | $37,088 |  Volcano Enginenot scored · read Nov 1 · receipt |
MiniMax-M3.1-Flash · related