ToolSite DeepSeek V4.1 Flash VRAM requirements
DeepSeek V4.1 Flash has 763.2B parameters, of which about 16B are used per token; all 384 experts still have to be in memory. With an 8K-token context and one request it needs about 474 GB of GPU memory at Q4_K_M, 783 GB at FP8 and 1,565 GB at FP16/BF16. The published weights take 475 GB (5.3 bits/weight). No single GPU in the table holds it at Q4_K_M; it needs a multi-GPU setup.
Open DeepSeek V4.1 Flash 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 (5.3 bits/weight) | 475 GB | 524 GB | 4 × H200 |
| FP16 / BF16 | 1,422 GB | 1,565 GB | More than 8 GPUs |
| FP8 / INT8 | 711 GB | 783 GB | 8 × H200 |
| INT4 (AWQ / GPTQ) | 378 GB | 417 GB | 4 × H200 |
| GGUF Q8_0 | 755 GB | 832 GB | 8 × H200 |
| GGUF Q6_K | 583 GB | 642 GB | 4 × B200 |
| GGUF Q5_K_M | 504 GB | 555 GB | 4 × H200 |
| GGUF Q4_K_M | 430 GB | 474 GB | 4 × H200 |
| GGUF Q3_K_M | 347 GB | 383 GB | 4 × H200 |
| GGUF Q2_K | 298 GB | 329 GB | 2 × B200 |
KV cache at long context
All 40 layers use full attention. Each extra token of context adds 80 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 | 320 MB | 160 MB | 474 GB |
| 32K tokens | 2.50 GB | 1.25 GB | 476 GB |
| 128K tokens | 10.0 GB | 5.00 GB | 485 GB |
| 1M tokens | 80.0 GB | 40.0 GB | 562 GB |
Which GPUs can run DeepSeek V4.1 Flash
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 more than 8 | Needs more than 8 |
| A100 40GB | 40 GB | Needs more than 8 | Needs more than 8 |
| Mac, 64 GB unified memory about 75% of it is usable by the GPU by default | 48 GB | Needs more than 8 | Needs more than 8 |
| L40S / RTX 6000 Ada | 48 GB | Needs more than 8 | Needs more than 8 |
| A100 / H100 80GB | 80 GB | Needs 8 | Needs more than 8 |
| Mac, 128 GB unified memory about 75% of it is usable by the GPU by default | 96 GB | Needs 8 | Needs more than 8 |
| H200 | 141 GB | Needs 4 | Needs 8 |
| B200 | 180 GB | Needs 4 | Needs 8 |
How fast DeepSeek V4.1 Flash 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 | — | — |
| 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
- 763.2B (763,205,315,794)
- Experts
- 384 routed experts, all loaded
- Active per token
- 16B
- Layers
- All 40 layers use full attention
- Attention cache
- 1 KV heads × 512
- Context length
- 1,048,576 tokens
- Published weights
- 475 GB (5.3 bits/weight)
- On Hugging Face
- deepseek-ai/DeepSeek-V4.1-Flash
Other models
- DeepSeek V4 Flash 0731
- 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 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 .