Xiaomi · Chat and reasoning · 311B parameters · 15B active · mit
MiMo V2.6 Flash RL
Needs 214 GB at INT4 / MXFP4. The smallest real configuration today is 8× Tesla V100 32GB at Vast.ai, $0.54 per hour, about $391 a month at 730 hours.
Parameters311B15B active per token
Context1M tokensmaximum published
Checkpoint178 GBINT4-packed, as published
Licensemitcheck before commercial use
ReleasedSep 22, 2026documented date
Smallest configuration · INT4 / MXFP4
8× Tesla V100 32GB256 GB VRAM · 83% used
- Per hour
- $0.54
- Per month
- $391
- Cheapest at
Vast.ai
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 | 178 GB | 214 GB | 214 GB | 219 GB | 233 GB | 252 GB | 368 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 5 GB | 20 GB | 39 GB | 155 GB |
Cross-checked on Hugging Face Oct 28, 2026: 310.8B parameters in the safetensors headers, 177.7 GB of weight files, attention layout from config.json (48 layers, 4 KV heads × 192). 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 = 3072 bytes per token per layer × 48 full-attention layers (FP16 cache, one sequence).config.json ↗
Smallest configuration per GPU · 109 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 |
|---|---|---|---|---|---|
| Tesla V100 32GBBest fit | 8× 32 GB256 GB total | 83% | $0.54 | $391 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.69, Edgevana $2.21 |
| MI325X | 1× 256 GB256 GB total | 83% | $2.25 | $1,643 |  OpenRelaynot scored · read Nov 2 · receipt · also Cyfuture AI $3.14, DigitalOcean $3.80 |
| A100 80GB | 4× 80 GB320 GB total | 67% | $2.40 | $1,754 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $4.60, Gcore $5.63 |
| A100 40GB | 8× 40 GB320 GB total | 67% | $3.20 | $2,338 | Vast.aiTrust 78 · read Nov 2 · receipt · also Denvr Cloud $9.20, Sesterce Cloud $12.32 |
| RTX A6000 | 8× 48 GB384 GB total | 56% | $3.36 | $2,453 |  LiumTrust 40 · read Nov 2 · receipt · also LeaderGPU $3.58, Verda $6.62 |
| L40S | 8× 48 GB384 GB total | 56% | $3.74 | $2,727 | Vast.aiTrust 78 · read Nov 2 · receipt · also Lium $6.00, GPU.ai $6.40 |
| RTX 5090 | 8× 32 GB256 GB total | 83% | $3.84 | $2,804 | Vast.aiTrust 78 · read Nov 2 · receipt · also Lium $4.00, Edgevana $5.28 |
| RTX PRO 6000 | 4× 96 GB384 GB total | 56% | $3.84 | $2,805 | Vast.aiTrust 78 · read Nov 2 · receipt · also UpCloud $3.89, Hetzner $6.44 |
| MI350X | 1× 288 GB288 GB total | 74% | $3.99 | $2,913 | OpenRelaynot scored · read Nov 2 · receipt |
| Gaudi 2 | 4× 96 GB384 GB total | 56% | $4.18 | $3,052 |  Cyfuture AInot scored · read Nov 2 · receipt |
| A40 | 8× 48 GB384 GB total | 56% | $4.61 | $3,364 |  LeaderGPUTrust 59 · read Nov 2 · receipt · also Exoscale $8.36 |
| A100X | 4× 80 GB320 GB total | 67% | $5.12 | $3,739 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 6000 Ada | 8× 48 GB384 GB total | 56% | $5.20 | $3,796 |  GPU.ainot scored · read Nov 2 · receipt · also io.net $5.46, QuantaCloud $6.21 |
| H200 NVL | 2× 141 GB282 GB total | 76% | $5.33 | $3,894 | Vast.aiTrust 78 · read Nov 2 · receipt · also IONOS $6.52, Geodd $6.78 |
| B300 | 1× 270 GB270 GB total | 79% | $5.57 | $4,070 |  SeewebTrust 69 · read Nov 2 · receipt · also UpCloud $5.82, Deep Infra $5.89 |
| MI300X | 2× 192 GB384 GB total | 56% | $5.71 | $4,167 | Cyfuture AInot scored · read Nov 2 · receipt · also Hot Aisle $5.98, AtmosCompute $6.69 |
| MI355X | 1× 288 GB288 GB total | 74% | $5.99 | $4,373 |  Daytonanot scored · read Nov 2 · receipt · also OpenRelay $6.30 |
| H100 | 4× 80 GB320 GB total | 67% | $6.84 | $4,991 |  GcoreTrust 80 · read Nov 2 · receipt · also GPU.ai $7.92, Edgevana $7.98 |
| H200 | 2× 141 GB282 GB total | 76% | $7.38 | $5,387 |  Theta EdgeCloudnot scored · read Nov 2 · receipt · also Vast.ai $7.53, Canopy Wave $8.00 |
| B200 | 2× 180 GB360 GB total | 59% | $8.22 | $6,002 |  UpCloudTrust 75 · read Nov 2 · receipt · also Deep Infra $9.78, Elice AI Cloud $13.64 |
| L40 | 8× 48 GB384 GB total | 56% | $8.40 | $6,132 |  OblivusTrust 82 · read Nov 2 · receipt · also CoreWeave $10.00, AtmosCompute $12.21 |
| RTX PRO 4500 | 8× 32 GB256 GB total | 83% | $9.91 | $7,235 |  AceCloudTrust 68 · read Nov 2 · receipt · also EmpirioLabs AI $11.20 |
| GB300 | 1× 279 GB279 GB total | 76% | $13.05 | $9,527 |  VerdaTrust 81 · read Nov 2 · receipt · also Fireworks AI $20.00 |
| H100 NVL | 4× 94 GB376 GB total | 57% | $17.86 | $13,038 |  AtmosComputenot scored · read Nov 2 · receipt · also EmpirioLabs AI $22.40, Open Telekom Cloud $25.90 |
| The 24 cheapest of 27 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
Throughput estimates · Oct 4, 2026Tokens per second, and what a million costs
Chat and reasoning. Speed estimated from memory bandwidth and model size, never measured. The cost per 1M output tokens is an estimate at the prices read on Oct 4, 2026; it is not recomputed here.
| GPU | Cards | Precision | tok/s per user | per 1M output tokens · estimate |
|---|---|---|---|---|
| B200 | 2 | FP4 | 118 | $0.853 |
| MI300X | 1 | FP4 | 102 | $0.916 |
| H200 | 2 | FP4 | 88.4 | $0.945 |
| A100 80GB | 4 | FP4 | 56.6 | $1.04 |
| H100 SXM | 4 | FP4 | 69.6 | $1.21 |
| H100 PCIe | 4 | FP4 | 42.7 | $1.69 |
| RTX PRO 6000 | 2 | FP4 | 52.6 | $2.20 |
| L40S | 4 | FP4 | 35.2 | $6.48 |
cards, precision and speed estimated from memory bandwidth and model size; cost recomputed by the site from verified prices · cheapest per output at the prices of Oct 4, 2026: B200 SXMWhy estimates, and their limits →
MiMo V2.6 Flash RL · related