ToolSite DeepSeek V4 Flash 0731 VRAM requirements
DeepSeek V4 Flash 0731 has 304.2B parameters, of which about 13B are used per token; all 256 experts still have to be in memory. With an 8K-token context and one request it needs about 190 GB of GPU memory at Q4_K_M, 313 GB at FP8 and 624 GB at FP16/BF16. The published weights take 155 GB (4.4 bits/weight). No single GPU in the table holds it at Q4_K_M; it needs a multi-GPU setup.
Open DeepSeek V4 Flash 0731 in the calculator
VRAM by quantization
Weights plus the KV cache for 8,192 tokens in FP16 and the runtime overhead (0.5 GB plus 10%). Each row opens the calculator with that setting. What the GGUF names mean.
| Precision | Weights | Total | Smallest setup |
|---|---|---|---|
| As published (4.4 bits/weight) | 155 GB | 172 GB | B200 |
| FP16 / BF16 | 567 GB | 624 GB | 4 × B200 |
| FP8 / INT8 | 283 GB | 313 GB | 2 × B200 |
| INT4 (AWQ / GPTQ) | 150 GB | 167 GB | B200 |
| GGUF Q8_0 | 301 GB | 332 GB | 2 × B200 |
| GGUF Q6_K | 232 GB | 257 GB | 2 × H200 |
| GGUF Q5_K_M | 201 GB | 222 GB | 2 × H200 |
| GGUF Q4_K_M | 171 GB | 190 GB | 2 × H200 |
| GGUF Q3_K_M | 138 GB | 154 GB | B200 |
| GGUF Q2_K | 119 GB | 132 GB | H200 |
KV cache at long context
All 43 layers use full attention. Each extra token of context adds 86 KB of FP16 cache per request. This model shares and compresses its KV cache across layers, which the calculator does not model, so the KV cache figure is an upper bound. How the KV cache works.
| Context | KV cache, FP16 | KV cache, FP8 | Total at Q4_K_M |
|---|---|---|---|
| 4K tokens | 344 MB | 172 MB | 189 GB |
| 32K tokens | 2.69 GB | 1.34 GB | 192 GB |
| 128K tokens | 10.8 GB | 5.38 GB | 201 GB |
| 1M tokens | 86.0 GB | 43.0 GB | 284 GB |
Which GPUs can run DeepSeek V4 Flash 0731
With 8,192 tokens of context. Several GPUs means one tensor-parallel group of 2, 4 or 8 cards.
| GPU | Memory | Q4_K_M | FP8 |
|---|---|---|---|
| RTX 3060 | 12 GB | Needs more than 8 | Needs more than 8 |
| RTX 4060 Ti 16GB | 16 GB | Needs more than 8 | Needs more than 8 |
| RTX 3090 / 4090 | 24 GB | Needs more than 8 | Needs more than 8 |
| RTX 5090 | 32 GB | Needs 8 | Needs more than 8 |
| A100 40GB | 40 GB | Needs 8 | Needs 8 |
| Mac, 64 GB unified memory about 75% of it is usable by the GPU by default | 48 GB | Needs 4 | Needs 8 |
| L40S / RTX 6000 Ada | 48 GB | Needs 4 | Needs 8 |
| A100 / H100 80GB | 80 GB | Needs 4 | Needs 4 |
| Mac, 128 GB unified memory about 75% of it is usable by the GPU by default | 96 GB | Needs 2 | Needs 4 |
| H200 | 141 GB | Needs 2 | Needs 4 |
| B200 | 180 GB | Needs 2 | Needs 2 |
How fast DeepSeek V4 Flash 0731 writes
Tokens per second for one request with 8,192 tokens of context, estimated from memory bandwidth and the parameters read per token. A dash means it does not fit on one card. Try other settings in the speed calculator.
| Hardware | Bandwidth | Q4_K_M | FP8 |
|---|---|---|---|
| RTX 3060 12GB | 360 GB/s | — | — |
| RTX 4090 | 1,008 GB/s | — | — |
| RTX 5090 | 1,792 GB/s | — | — |
| M4 Max Mac (128 GB) | 546 GB/s | — | — |
| M3 Ultra Mac Studio (512 GB) | 819 GB/s | 27–47 | 17–29 |
| H100 SXM | 3,350 GB/s | — | — |
| H200 | 4,800 GB/s | — | — |
Longest context on one GPU
How many tokens of context fit on a single card with one request and an FP16 KV cache. "Full" means the model's whole context window fits.
| GPU | Memory | Q4_K_M | Q8_0 | FP8 |
|---|---|---|---|---|
| RTX 3060 | 12 GB | No | No | No |
| RTX 4060 Ti 16GB | 16 GB | No | No | No |
| RTX 3090 / 4090 | 24 GB | No | No | No |
| RTX 5090 | 32 GB | No | No | No |
| A100 40GB | 40 GB | No | No | No |
| Mac, 64 GB unified memory | 48 GB | No | No | No |
| L40S / RTX 6000 Ada | 48 GB | No | No | No |
| A100 / H100 80GB | 80 GB | No | No | No |
| Mac, 128 GB unified memory | 96 GB | No | No | No |
| H200 | 141 GB | No | No | No |
| B200 | 180 GB | No | No | No |
Model details
- Parameters
- 304.2B (304,180,418,494)
- Experts
- 256 routed experts, all loaded
- Active per token
- 13B
- Layers
- All 43 layers use full attention
- Attention cache
- 1 KV heads × 512
- Context length
- 1,048,576 tokens
- Published weights
- 155 GB (4.4 bits/weight)
- On Hugging Face
- deepseek-ai/DeepSeek-V4-Flash-0731
Other models
- Qwen3.6 35B-A3B
- Qwen3.6 27B
- Qwen3.8 27B
- Qwen3.8 Flash Next
- Qwen3.8 2.4T-A95B
- Qwen3.5 9B
- Qwen3.5 122B-A10B
- Qwen3-Coder-Next
- DeepSeek V4.1 Flash
- DeepSeek V4 Flash
- DeepSeek V4 Pro
- DeepSeek V3.2
- GLM-5.3
- GLM-5.3 Flash
- GLM-5.2
- GLM-4.7 Flash
- Gemma 4 31B
- Gemma 4 26B-A4B
- Gemma 4 12B
- Gemma 4 E4B
- Kimi K3
- MiniMax M3
- MiniMax M2.7
- MiMo V2.6 Flash
- MiMo V2.6 Pro
- Mistral Medium 3.5 128B
- Nemotron 3 Nano 4B
- Nemotron 3 Nano 30B-A3B
- Nemotron 3 Super 120B-A12B
- Xing 4.0 29B-A4B
- Muse Glimmer 30B
- MiniCPM5 2B
- Llama 3.1 8B
- Llama 3.1 70B
- Qwen3 8B
- Qwen3 30B-A3B
- gpt-oss-20b
- gpt-oss-120b
- DeepSeek V3 / R1
Numbers read from the model files on Hugging Face on .