Atria Dawn
Needs 904 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 Atria Dawn
news checked 2026-10-27Agentic model 'built on the 744B-parameter MoE GLM-5.2 foundation model' (card), with the same memory profile as GLM-5.2. The README table lists a 512K context for the full release; config max_position_embeddings is 1,048,576. The full release replaces Atria Dawn Preview (MIT, 256K, HF 2026-09-11). Text-only. HF first commit 2026-10-23. One October secondary source still listed the full BF16/FP8 downloads as 'forthcoming'; they are now on HF. MLA kv_lora 512. The config head_dim (64) differs from the Preview's 192.
- https://huggingface.co/internlm/Atria-Dawn
- https://huggingface.co/internlm/Atria-Dawn/raw/main/config.json
- https://huggingface.co/api/models/internlm/Atria-Dawn?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 | 1,507 GB | 1,809 GB | 1,809 GB | 1,811 GB | 1,820 GB | 1,832 GB | 1,903 GB |
| FP8 / INT8estimated | 753 GB | 904 GB | 905 GB | 907 GB | 916 GB | 928 GB | 999 GB |
| INT4 / MXFP4estimated | 452 GB | 543 GB | 543 GB | 546 GB | 555 GB | 566 GB | 637 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 3 GB | 12 GB | 24 GB | 95 GB |
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 |
|---|---|---|---|---|---|
| MI325XBest fit | 4× 256 GB1024 GB total | 88% | $12.29 | $8,972 | Cyfuture AInot scored · read Nov 2 · receipt |
| MI300X | 8× 192 GB1536 GB total | 59% | $13.68 | $9,986 |  TensorWaveTrust 64 · read Nov 2 · receipt · also Cyfuture AI $22.38, AtmosCompute $26.77 |
| H200 | 8× 141 GB1128 GB total | 80% | $21.04 | $15,359 |  Airon AInot scored · read Nov 2 · receipt · also Geodd $21.76, Lium $23.92 |
| B300 | 4× 288 GB1152 GB total | 78% | $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 | 39% | $23.60 | $17,228 | TensorWaveTrust 64 · read Nov 2 · receipt |
| H200 NVL | 8× 141 GB1128 GB total | 80% | $26.09 | $19,042 |  IONOSnot scored · read Nov 2 · receipt · also Geodd $27.12, Vast.ai $39.47 |
| B200 | 8× 180 GB1440 GB total | 63% | $32.91 | $24,026 | UpCloudTrust 75 · read Nov 2 · receipt · also Airon AI $33.04, Deep Infra $39.12 |
| B300 CC | 4× 288 GB1152 GB total | 78% | $46.31 | $33,806 |  VerdaTrust 81 · read Nov 2 · receipt |
| GB300 | 4× 288 GB1152 GB total | 78% | $52.21 | $38,113 | VerdaTrust 81 · read Nov 2 · receipt |
| B200 CC | 8× 180 GB1440 GB total | 63% | $72.37 | $52,830 | VerdaTrust 81 · read Nov 2 · receipt |
Atria Dawn · related