Z.ai · Chat and reasoning · 357B parameters · 32B active · mit
GLM-4.6
Needs 429 GB at FP8 / INT8. The smallest real configuration today is 2× MI325X at Cyfuture AI, $6.21 per hour, about $4,536 a month at 730 hours.
Parameters357B32B active per token
Context198k tokensmaximum published
Checkpoint714 GBBF16, as published
Licensemitcheck before commercial use
Released—documented date
Smallest configuration · FP8 / INT8
2× MI325X512 GB VRAM · 84% used
- Per hour
- $6.21
- Per month
- $4,536
- Cheapest at
Cyfuture AI
Memory · 3 precisions · 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 | 198k context |
|---|---|---|---|---|---|---|
| BF16published checkpoint | 714 GB | 857 GB | 858 GB | 869 GB | 906 GB | 933 GB |
| FP8 / INT8estimated | 357 GB | 429 GB | 430 GB | 441 GB | 478 GB | 505 GB |
| INT4 / MXFP4estimated | 214 GB | 258 GB | 259 GB | 270 GB | 307 GB | 334 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 2 GB | 13 GB | 50 GB | 77 GB |
Cross-checked on Hugging Face Oct 28, 2026: 356.8B parameters in the safetensors headers, 713.6 GB of weight files, attention layout from config.json (92 layers, 8 KV heads × 128). 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 = 4096 bytes per token per layer × 92 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 |
|---|---|---|---|---|---|
| MI325XBest fit | 2× 256 GB512 GB total | 84% | $6.21 | $4,536 | Cyfuture AInot scored · read Nov 2 · receipt |
| RTX PRO 6000 | 8× 96 GB768 GB total | 56% | $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 | 56% | $8.27 | $6,036 | Cyfuture AInot scored · read Nov 2 · receipt |
| A100 80GB | 8× 80 GB640 GB total | 67% | $8.54 | $6,231 |  Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $9.82, GPU.ai $10.00 |
| H200 NVL | 4× 141 GB564 GB total | 76% | $10.67 | $7,788 | Vast.aiTrust 78 · read Nov 2 · receipt · also IONOS $13.04, Geodd $13.56 |
| MI300X | 4× 192 GB768 GB total | 56% | $11.31 | $8,257 | Cyfuture AInot scored · read Nov 2 · receipt · also Hot Aisle $11.96, AtmosCompute $13.38 |
| B300 | 2× 270 GB540 GB total | 79% | $11.65 | $8,506 | UpCloudTrust 75 · read Nov 2 · receipt · also FPT AI Factory $13.98, Vast.ai $17.00 |
| H100 | 8× 80 GB640 GB total | 67% | $13.67 | $9,982 |  GcoreTrust 80 · read Nov 2 · receipt · also Airon AI $15.04, UpCloud $16.00 |
| H200 | 4× 141 GB564 GB total | 76% | $14.76 | $10,775 |  Theta EdgeCloudnot scored · read Nov 2 · receipt · also Canopy Wave $16.00, Hugging Face $20.00 |
| B200 | 4× 180 GB720 GB total | 60% | $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 | 57% | $16.48 | $12,030 |  GPU.ainot scored · read Nov 2 · receipt · also Spheron $21.97, AtmosCompute $35.73 |
| MI355X | 8× 288 GB2304 GB total | 19% | $23.60 | $17,228 |  TensorWaveTrust 64 · read Nov 2 · receipt |
| GB300 | 2× 279 GB558 GB total | 77% | $26.11 | $19,060 |  VerdaTrust 81 · read Nov 2 · receipt |
| B200 CC | 4× 180 GB720 GB total | 60% | $36.19 | $26,419 | VerdaTrust 81 · read Nov 2 · receipt |
| B300 CC | 4× 270 GB1080 GB total | 40% | $46.31 | $33,806 | VerdaTrust 81 · read Nov 2 · receipt |
| A800 80GB PCIe | 8× 80 GB640 GB total | 67% | $50.80 | $37,088 |  Volcano Enginenot scored · 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 | 4 | FP8 | 27.6 | $2.18 |
| H200 | 4 | FP8 | 35.8 | $2.68 |
| B200 | 4 | FP8 | 48.5 | $2.90 |
| H100 SXM | 8 | FP8 | 29.6 | $3.87 |
| RTX PRO 6000 | 8 | FP8 | 18.4 | $5.31 |
| H100 PCIe | 8 | FP8 | 17.3 | $5.90 |
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 →
GLM-4.6 · related