Meituan · Chat and reasoning · 562B parameters · 27B active · mit
LongCat Flash Chat
Needs 675 GB at FP8 / INT8. The smallest real configuration today is 8× RTX PRO 6000 at UpCloud, $7.78 per hour, about $5,676 a month at 730 hours.
Parameters562B27B active per token
Context128k tokensmaximum published
Checkpoint1,124 GBBF16, as published
Licensemitcheck before commercial use
Released—documented date
Smallest configuration · FP8 / INT8
8× RTX PRO 6000768 GB VRAM · 88% used
- Per hour
- $7.78
- Per month
- $5,676
- Cheapest at
UpCloud
Memory · 3 precisions · 4 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 |
|---|---|---|---|---|---|
| BF16published checkpoint | 1,124 GB | 1,349 GB | 1,349 GB | 1,350 GB | 1,354 GB |
| FP8 / INT8estimated | 562 GB | 675 GB | 675 GB | 676 GB | 679 GB |
| INT4 / MXFP4estimated | 337 GB | 405 GB | 405 GB | 406 GB | 409 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 2 GB | 5 GB |
Cross-checked on Hugging Face Oct 28, 2026: 561.9B parameters in the safetensors headers, 1124.0 GB of weight files, attention layout from config.json (28 layers, latent rank 512). 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 = 1152 bytes per token per layer × 28 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 |
|---|---|---|---|---|---|
| RTX PRO 6000Best fit | 8× 96 GB768 GB total | 88% | $7.78 | $5,676 | UpCloudTrust 75 · read Nov 1 · receipt · also Vast.ai $10.14, Lium $12.80 |
| Gaudi 2 | 8× 96 GB768 GB total | 88% | $8.27 | $6,036 |  Cyfuture AInot scored · read Nov 1 · receipt |
| MI300X | 4× 192 GB768 GB total | 88% | $11.31 | $8,257 | Cyfuture AInot scored · read Nov 1 · receipt · also Hot Aisle $11.96, AtmosCompute $13.38 |
| MI325X | 4× 256 GB1024 GB total | 66% | $12.29 | $8,972 | Cyfuture AInot scored · read Nov 1 · receipt |
| B200 | 4× 180 GB720 GB total | 94% tight | $16.46 | $12,013 | UpCloudTrust 75 · read Nov 1 · receipt · also Deep Infra $19.56, Lambda $27.16 |
| H200 | 8× 141 GB1128 GB total | 60% | $21.04 | $15,359 |  Airon AInot scored · read Nov 1 · receipt · also Geodd $21.76, Vast.ai $22.11 |
| B300 | 4× 288 GB1152 GB total | 59% | $23.29 | $17,004 | UpCloudTrust 75 · read Nov 1 · receipt · also FPT AI Factory $27.96, Vast.ai $37.50 |
| MI355X | 8× 288 GB2304 GB total | 29% | $23.60 | $17,228 |  TensorWaveTrust 64 · read Nov 1 · receipt |
| H200 NVL | 8× 141 GB1128 GB total | 60% | $26.09 | $19,042 |  IONOSnot scored · read Nov 1 · receipt · also Geodd $27.12, Vast.ai $39.47 |
| B200 CC | 4× 180 GB720 GB total | 94% tight | $36.19 | $26,419 |  VerdaTrust 81 · read Nov 1 · receipt |
| B300 CC | 4× 288 GB1152 GB total | 59% | $46.31 | $33,806 | VerdaTrust 81 · read Nov 1 · receipt |
| H100 NVL | 8× 94 GB752 GB total | 90% | $51.79 | $37,809 |  Open Telekom Cloudnot scored · read Nov 1 · receipt · also Cloud.ru $52.63 |
| GB300 | 4× 288 GB1152 GB total | 59% | $52.21 | $38,113 | VerdaTrust 81 · read Nov 1 · receipt |
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 |
|---|---|---|---|---|
| MI300X | 4 | FP8 | 69.9 | $1.99 |
| B200 | 4 | FP8 | 121 | $2.56 |
| H200 | 8 | FP8 | 84.0 | $3.31 |
| RTX PRO 6000 | 8 | FP8 | 44.7 | $5.25 |
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: MI300XWhy estimates, and their limits →
LongCat Flash Chat · related