Moonshot AI · Chat and reasoning · 1T parameters · 32B active · modified-mit
Kimi K2.5
Needs 715 GB at INT4 / MXFP4. The smallest real configuration today is 8× RTX PRO 6000 at UpCloud, $7.78 per hour, about $5,676 a month at 730 hours.
Parameters1T32B active per token
Context256k tokensmaximum published
Checkpoint595 GBINT4-packed, as published
Licensemodified-mitcheck before commercial use
Released—documented date
Smallest configuration · INT4 / MXFP4
8× RTX PRO 6000768 GB VRAM · 93% used
- Per hour
- $7.78
- Per month
- $5,676
- Cheapest at
UpCloud
Memory · 1 precision · 5 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 |
|---|---|---|---|---|---|---|
| INT4-packedpublished checkpoint | 595 GB | 715 GB | 715 GB | 717 GB | 724 GB | 733 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 3 GB | 10 GB | 19 GB |
Cross-checked on Hugging Face Oct 28, 2026: 1026.9B parameters in the safetensors headers, 595.2 GB of weight files, attention layout from config.json (61 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 × 61 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 |
|---|---|---|---|---|---|
| RTX PRO 6000Best fit | 8× 96 GB768 GB total | 93% tight | $7.78 | $5,676 | UpCloudTrust 75 · read Nov 2 · receipt · also Vast.ai $9.58, Lium $12.80 |
| Gaudi 2 | 8× 96 GB768 GB total | 93% tight | $8.27 | $6,036 |  Cyfuture AInot scored · read Nov 2 · receipt |
| MI300X | 4× 192 GB768 GB total | 93% tight | $11.31 | $8,257 | Cyfuture AInot scored · read Nov 2 · receipt · also Hot Aisle $11.96, AtmosCompute $13.38 |
| MI325X | 4× 256 GB1024 GB total | 70% | $12.29 | $8,972 | Cyfuture AInot scored · read Nov 2 · receipt |
| B200 | 4× 180 GB720 GB total | 99% tight | $16.46 | $12,013 | UpCloudTrust 75 · read Nov 2 · receipt · also Deep Infra $19.56, Lambda $27.16 |
| H100 NVL | 8× 94 GB752 GB total | 95% tight | $16.48 | $12,030 |  GPU.ainot scored · read Nov 2 · receipt · also Spheron $21.97, AtmosCompute $35.73 |
| H200 | 8× 141 GB1128 GB total | 63% | $21.04 | $15,359 |  Airon AInot scored · read Nov 2 · receipt · also Geodd $21.76, Lium $23.92 |
| B300 | 4× 270 GB1080 GB total | 66% | $23.29 | $17,004 | UpCloudTrust 75 · read Nov 2 · receipt · also FPT AI Factory $27.96, Verda $45.40 |
| MI355X | 8× 288 GB2304 GB total | 31% | $23.60 | $17,228 |  TensorWaveTrust 64 · read Nov 2 · receipt |
| H200 NVL | 8× 141 GB1128 GB total | 63% | $26.09 | $19,042 |  IONOSnot scored · read Nov 2 · receipt · also Geodd $27.12, Vast.ai $39.47 |
| B200 CC | 4× 180 GB720 GB total | 99% tight | $36.19 | $26,419 |  VerdaTrust 81 · read Nov 2 · receipt |
| B300 CC | 4× 270 GB1080 GB total | 66% | $46.31 | $33,806 | VerdaTrust 81 · read Nov 2 · receipt |
| GB300 | 4× 279 GB1116 GB total | 64% | $52.21 | $38,113 | VerdaTrust 81 · read Nov 2 · receipt |
Kimi K2.5 · related