Tongyi Lab · Image generation · 6.16B parameters · apache-2.0
Z-Image
Needs 8 GB at FP8 / INT8. The smallest real configuration today is 1× RTX 3060 at Vast.ai, $0.04 per hour, about $26 a month at 730 hours.
Parameters6.16Bdense
CategoryImage generationsized on weights + headroom
Checkpoint21 GBBF16, as published
Licenseapache-2.0check before commercial use
Released—documented date
Smallest configuration · FP8 / INT8
1× RTX 306012 GB VRAM · 62% used
- Per hour
- $0.04
- Per month
- $26
- Cheapest at
Vast.ai
Memory · 3 precisionsHow much VRAM it needs
Weights plus 20% runtime overhead. For image generation models, activations also depend on resolution, clip length and batch size; the per-GPU estimates below give the practical configuration.
| Precision | Weights | Weights + headroom |
|---|---|---|
| BF16published checkpoint | 21 GB | 25 GB |
| FP8 / INT8estimated | 6 GB | 8 GB |
| INT4 / MXFP4estimated | 4 GB | 5 GB |
Cross-checked on Hugging Face Oct 28, 2026: 6.15B parameters in the safetensors headers, 20.5 GB of weight files. 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 not added (architecture not readable).
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 |
|---|---|---|---|---|---|
| RTX 3060Best fit | 1× 12 GB12 GB total | 62% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.05, gcube $0.05 |
| RTX A2000 | 1× 12 GB12 GB total | 62% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 1 · receipt · also gcube $0.09 |
| Tesla P4 | 1× 8 GB8 GB total | 92% tight | $0.04 | $29 | Vast.aiTrust 78 · read Nov 1 · receipt · also Akash Network $0.06, gcube $0.07 |
| T4 | 1× 16 GB16 GB total | 46% | $0.04 | $29 | Vast.aiTrust 78 · read Nov 1 · receipt · also iwinv $0.20, Theta EdgeCloud $0.20 |
| Tesla P40 | 1× 24 GB24 GB total | 31% | $0.04 | $30 |  Clore.aiTrust 46 · read Nov 1 · receipt · also gcube $0.07, Vast.ai $0.11 |
| GTX Titan X | 1× 12 GB12 GB total | 62% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 1 · receipt |
| Titan Xp | 1× 12 GB12 GB total | 62% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 1 · receipt |
| GTX 1080 | 1× 8 GB8 GB total | 92% tight | $0.04 | $32 | Vast.aiTrust 78 · read Nov 1 · receipt · also Edgevana $0.06 |
| Tesla P100 | 1× 16 GB16 GB total | 46% | $0.04 | $33 | Vast.aiTrust 78 · read Nov 1 · receipt · also gcube $0.07 |
| GTX 1070 | 1× 8 GB8 GB total | 92% tight | $0.05 | $36 | Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.08 |
| RTX 4060 | 1× 8 GB8 GB total | 92% tight | $0.05 | $40 | Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.08, Theta EdgeCloud $0.09 |
| RTX 2070 | 1× 8 GB8 GB total | 92% tight | $0.06 | $41 | Vast.aiTrust 78 · read Nov 1 · receipt · also gcube $0.06, Clore.ai $0.21 |
| RTX 3060 Ti | 1× 8 GB8 GB total | 92% tight | $0.06 | $41 | Vast.aiTrust 78 · read Nov 1 · receipt · also gcube $0.06, Clore.ai $0.06 |
| RTX 2060 Super | 1× 8 GB8 GB total | 92% tight | $0.06 | $41 | |
| Quadro P2000 | 2× 5 GB10 GB total | 74% | $0.06 | $41 | Vast.aiTrust 78 · read Nov 1 · receipt |
| GTX 1070 Ti | 1× 8 GB8 GB total | 92% tight | $0.06 | $44 | Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.10 |
| RTX 2070 Super | 1× 8 GB8 GB total | 92% tight | $0.06 | $44 | |
| RTX 3070 | 1× 8 GB8 GB total | 92% tight | $0.06 | $44 | |
| GTX 1080 Ti | 1× 11 GB11 GB total | 67% | $0.06 | $45 | Vast.aiTrust 78 · read Nov 1 · receipt · also Edgevana $0.08 |
| RTX A4000 | 1× 16 GB16 GB total | 46% | $0.06 | $46 | Clore.aiTrust 46 · read Nov 1 · receipt · also Vast.ai $0.07, Edgevana $0.10 |
| Tesla V100 16GB | 1× 16 GB16 GB total | 46% | $0.06 | $46 | Clore.aiTrust 46 · read Nov 1 · receipt · also Vast.ai $0.08, CloudRift $0.28 |
| RTX 2080 | 1× 8 GB8 GB total | 92% tight | $0.06 | $47 | |
| RTX 2080 Super | 1× 8 GB8 GB total | 92% tight | $0.06 | $47 | |
| RTX 2080 Ti | 1× 11 GB11 GB total | 67% | $0.07 | $49 | |
| The 24 cheapest of 104 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
Throughput estimates · Oct 4, 2026Estimated speed, in s per image
Image generation. Speed estimated from memory bandwidth and model size, never measured. The cost per 1,000 images is an estimate at the prices read on Oct 4, 2026; it is not recomputed here.
| GPU | Cards | Precision | s per image | per 1,000 images · estimate |
|---|---|---|---|---|
| RTX 4090 | 1 | FP8 | 4.9 | $0.310 |
| RTX 5090 | 1 | FP8 | 2.9 | $0.390 |
| L40S | 1 | FP8 | 4.0 | $0.620 |
| RTX PRO 6000 | 1 | FP8 | 2.1 | $0.660 |
| H100 SXM | 1 | FP8 | 1.7 | $0.850 |
| H100 PCIe | 1 | FP8 | 2.3 | $0.850 |
| B200 | 1 | FP8 | 0.8 | $0.950 |
| A100 80GB | 1 | BF16 | 3.9 | $1.02 |
| H200 | 1 | FP8 | 1.6 | $1.07 |
| MI300X | 1 | FP8 | 2.4 | $1.09 |
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: RTX 4090Why estimates, and their limits →
Z-Image · related