Qwen2.5-Coder-32B: GPU memory and hosting cost
Open weights · 32.76 billion parameters · 32,768-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 81.9 GB of GPU memory at bf16, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| Nebius | gpu-rtx6000-a.1gpu-24vcpu-218gb | 1 × RTX PRO 6000 96 GB | $1.80 | $1,314 |
| DeepInfra | h200.1x | 1 × H200 141 GB | $3.49 | $2,548 |
| Core42 | mi300x.1x | 1 × MI300X 192 GB | $3.50 | $2,555 |
| Google Cloud | g4-standard-48 | 1 × RTX PRO 6000 96 GB | $4.50 | $3,285 |
| HF Endpoints | aws.nvidia-h200.x1 | 1 × H200 141 GB | $5.00 | $3,650 |
| Azure | Standard_NC144ds_xl_RTXPRO6000BSE_v6 | 1 × RTX PRO 6000 96 GB | $6.38 | $4,657 |
| Alibaba Cloud | ecs.gn8v.4xlarge | 1 × GPU H 96 GB | $7.31 | $5,337 |
| Fireworks AI | h200.1x | 1 × H200 141 GB | $8.00 | $5,840 |
| IBM watsonx | deploy-on-demand.1xH200 | 1 × H200 141 GB | $16.00 | $11,680 |
| Crusoe | a100-sxm.8x | 8 × A100 80 GB | $18.40 | $13,432 |
| AWS | p4d.24xlarge | 8 × A100 40 GB | $21.96 | $16,029 |
| Together AI | hgx-h100.8gpu | 8 × H100 80 GB | $31.92 | $23,302 |
| OCI | BM.GPU.A100-v2.8 | 8 × A100 80 GB | $32.00 | $23,360 |
More from Unsloth
- Llama-3.2-1B-Instruct (unsloth)
- Llama-3.2-3B-Instruct (unsloth)
- Llama-3.1-8B-Instruct (unsloth)
- Meta-Llama-3.1-8B-Instruct (unsloth)
- Qwen2.5-Coder-7B-Instruct (unsloth)
- Qwen2.5-7B-Instruct (unsloth)
Similar size, open weights
List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.