GLM-5.3
Needs 907 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 GLM-5.3
news checked 2026-10-27Released 2026-08-27 under its own GLM-5.3 licence (GLM-5.2 and GLM-5.3-Flash stay MIT); 753B parameters, 40B active, FP8 checkpoint of 756 GB read on Hugging Face on 2026-10-27. Existence corroborated by third-party benchmarks and vLLM tickets.
- https://huggingface.co/zai-org/GLM-5.3
- https://huggingface.co/zai-org/GLM-5.3/raw/main/config.json
- https://huggingface.co/api/models/zai-org/GLM-5.3?blobs=true
Memory · 2 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 |
|---|---|---|---|---|---|---|---|
| FP8published checkpoint | 755 GB | 907 GB | 907 GB | 910 GB | 919 GB | 931 GB | 1,001 GB |
| INT4 / MXFP4estimated | 452 GB | 543 GB | 543 GB | 546 GB | 554 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 · 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 | 89% | $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× 270 GB1080 GB total | 84% | $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× 270 GB1080 GB total | 84% | $46.31 | $33,806 |  VerdaTrust 81 · read Nov 2 · receipt |
| GB300 | 4× 279 GB1116 GB total | 81% | $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 |
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 | 8 | FP8 | 26.7 | $4.59 |
| H200 | 8 | FP8 | 34.7 | $5.58 |
| B200 | 8 | FP8 | 46.6 | $6.10 |
GLM-5.3 · related