Muse Spark Open 816B-A42B
Needs 980 GB at FP8 / INT8. The smallest real configuration today is 4× MI325X at Cyfuture AI, $12.29 per hour, about $8,972 a month at 730 hours.
- Per hour
- $12.29
- Per month
- $8,972
- Cheapest at
Cyfuture AI
What is documented about Muse Spark Open 816B-A42B
news checked 2026-10-27MAJOR NEW RELEASE. Card: '816B total/42B active', 62 layers, 256 experts (8 active), '1M at inference'. Input: text, image, video and audio; output: text. Repo is gated (manual approval). HF counts 822.0B. kv heads, head_dim and context come from the public mirror config mlx-community/Muse-Spark-Open-816B-A42B-4bit because the official config is gated. 46 sliding (2048) + 16 full-attention layers. The HF repo was created 2026-09-15 but released 2026-10-15 (Meta/press).
- https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B
- https://huggingface.co/api/models/meta-models/Muse-Spark-Open-816B-A42B?blobs=true
- https://huggingface.co/api/models/meta-models/Muse-Spark-Open-816B-A42B-NVFP4?blobs=true
Memory · 3 precisions · 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 |
|---|---|---|---|---|---|---|---|
| BF16published checkpoint | 1,644 GB | 1,974 GB | 1,974 GB | 1,976 GB | 1,983 GB | 1,991 GB | 2,043 GB |
| FP8 / INT8estimated | 816 GB | 980 GB | 980 GB | 982 GB | 989 GB | 997 GB | 1,049 GB |
| INT4 / MXFP4estimated | 490 GB | 588 GB | 589 GB | 591 GB | 597 GB | 606 GB | 657 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 3 GB | 9 GB | 18 GB | 70 GB |
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 |
|---|---|---|---|---|---|
| MI325XBest fit | 4× 256 GB1024 GB total | 96% tight | $12.29 | $8,972 | Cyfuture AInot scored · read Nov 2 · receipt |
| MI300X | 8× 192 GB1536 GB total | 64% | $13.68 | $9,986 |  TensorWaveTrust 64 · read Nov 2 · receipt · also Cyfuture AI $22.38, AtmosCompute $26.77 |
| H200 | 8× 141 GB1128 GB total | 87% | $21.04 | $15,359 |  Airon AInot scored · read Nov 2 · receipt · also Geodd $21.76, Lium $23.92 |
| B300 | 4× 270 GB1080 GB total | 91% tight | $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 | 43% | $23.60 | $17,228 | TensorWaveTrust 64 · read Nov 2 · receipt |
| H200 NVL | 8× 141 GB1128 GB total | 87% | $26.09 | $19,042 |  IONOSnot scored · read Nov 2 · receipt · also Geodd $27.12, Vast.ai $39.47 |
| B200 | 8× 180 GB1440 GB total | 68% | $32.91 | $24,026 | UpCloudTrust 75 · read Nov 2 · receipt · also Airon AI $33.04, Deep Infra $39.12 |
| B300 CC | 4× 270 GB1080 GB total | 91% tight | $46.31 | $33,806 |  VerdaTrust 81 · read Nov 2 · receipt |
| GB300 | 4× 279 GB1116 GB total | 88% | $52.21 | $38,113 | VerdaTrust 81 · read Nov 2 · receipt |
| B200 CC | 8× 180 GB1440 GB total | 68% | $72.37 | $52,830 | VerdaTrust 81 · read Nov 2 · receipt |
Muse Spark Open 816B-A42B · related