Qwen3.6-35B-A3B-FP8: GPU memory and hosting cost
Open weights · 35.95 billion parameters · Mixture of experts · 262,144-token context · licence apache-2.0
No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.
Run it yourself
It needs 44.9 GB of GPU memory at fp8, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| DeepInfra | a100.1x | 1 × A100 80 GB | $1.49 | $1,088 |
| Crusoe | l40s.1x | 1 × L40S 48 GB | $1.50 | $1,095 |
| Nebius | gpu-l40s-a.1gpu-8vcpu-32gb | 1 × L40S 48 GB | $1.55 | $1,130 |
| HF Endpoints | aws.nvidia-l40s.x1 | 1 × L40S 48 GB | $1.80 | $1,314 |
| AWS | g6e.xlarge | 1 × L40S 48 GB | $1.86 | $1,359 |
| Alibaba Cloud | ecs.gn8is.2xlarge | 1 × L20 48 GB | $2.26 | $1,648 |
| Core42 | h100.1x | 1 × H100 80 GB | $2.50 | $1,825 |
| Azure | Standard_NC72ds_xl_RTXPRO6000BSE_v6 | 1 × RTX PRO 6000 48 GB | $2.83 | $2,066 |
| IBM watsonx | deploy-on-demand.1xL40S | 1 × L40S 48 GB | $4.43 | $3,234 |
| Google Cloud | g4-standard-48 | 1 × RTX PRO 6000 96 GB | $4.50 | $3,285 |
| Fireworks AI | h100.1x | 1 × H100 80 GB | $8.00 | $5,840 |
| OCI | BM.GPU.L40S.4 | 4 × L40S 48 GB | $14.00 | $10,220 |
| Together AI | hgx-h100.8gpu | 8 × H100 80 GB | $31.92 | $23,302 |
More from Qwen
- Qwen3.8 27B
- Qwen3 32B
- Qwen3 235B A22B Instruct 2507
- Qwen3.5 397B A17B
- Qwen3 30B A3B Instruct 2507
- Qwen3 235B A22B
Similar size, open weights
List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.