Mistral-Medium-3.5-128B-NVFP4: GPU memory and hosting cost
Open weights · 127.7 billion parameters · 262,144-token context · licence other
No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.
Run it yourself
It needs 79.8 GB of GPU memory at int4, 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 |
| Nebius | gpu-rtx6000-a.1gpu-24vcpu-218gb | 1 × RTX PRO 6000 96 GB | $1.80 | $1,314 |
| Crusoe | a100-pcie.1x | 1 × A100 80 GB | $2.00 | $1,460 |
| Core42 | h100.1x | 1 × H100 80 GB | $2.50 | $1,825 |
| HF Endpoints | aws.nvidia-a100.x1 | 1 × A100 80 GB | $2.50 | $1,825 |
| Azure | Standard_NC24ads_A100_v4 | 1 × A100 80 GB | $3.67 | $2,681 |
| Google Cloud | g4-standard-48 | 1 × RTX PRO 6000 96 GB | $4.50 | $3,285 |
| IBM watsonx | deploy-on-demand.1xA100 | 1 × A100 80 GB | $5.80 | $4,234 |
| AWS | p5.4xlarge | 1 × H100 80 GB | $6.88 | $5,022 |
| Alibaba Cloud | ecs.gn8v.4xlarge | 1 × GPU H 96 GB | $7.31 | $5,337 |
| Fireworks AI | h100.1x | 1 × H100 80 GB | $8.00 | $5,840 |
| 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 NVIDIA
- Qwen3.6-35B-A3B-NVFP4
- NVIDIA-Nemotron-3-Nano-4B-BF16
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- Gemma-4-26B-A4B-NVFP4
- Qwen2.5-VL-7B-Instruct-NVFP4
- NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Similar size, open weights
- OpenAI gpt-oss 120B
- Llama 3.3 70B
- Llama 4 Scout 17B
- Llama 3.1 70B
- MiniMax M2.5
- Qwen3 235B A22B Instruct 2507
List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.