How much VRAM does DeepSeek V4.1 Flash need?
DeepSeek V4.1 Flash needs 431 GB for its weights at 4-bit, 432 GB with an 8K context and 432 GB with 32K.
- Parameters
- 763B
- Active per token
- 16B
- Longest context
- 1M
- Released
- Sep 2026
- License
- MIT
- Strongest at
- Chat, Coding, Agents, Docs
Memory at each precision
| Precision | Weights | With 8K | With 32K | With 128K |
|---|---|---|---|---|
| As released (FP4 + FP8) | 475 GB | 476 GB | 476 GB | 476 GB |
| 4-bit | 431 GB | 432 GB | 432 GB | 432 GB |
| 3-bit | 347 GB | 348 GB | 348 GB | 349 GB |
| 2-bit | 267 GB | 267 GB | 267 GB | 268 GB |
| 1.6-bit | 147 GB | 147 GB | 148 GB | 148 GB |
One conversation, 16-bit context cache, runtime overhead included.
What runs it
| Machine | Best fit | Context | Speed | First reply |
|---|---|---|---|---|
| RTX 3060 12 GB | Too big | |||
| RTX 4060 Ti 16 GB | Too big | |||
| RTX 3090 | Too big | |||
| RTX 4090 | Too big | |||
| RTX 5090 | Too big | |||
| 2× RTX 3090 | Too big | |||
| RTX PRO 6000 Blackwell | Too big | |||
| M4 Max 128 GB | Too big | |||
| M5 Max 128 GB | Too big | |||
| Ryzen AI Max+ 395 128 GB | Too big | |||
| DGX Spark 128 GB | Too big | |||
| M3 Ultra 256 GB | 1.6-bit | 1M | 82 tok/s | 9.4 s |
| M5 Ultra 512 GB | 3-bit | 1M | 62 tok/s | 3.0 s |
| H100 SXM | Too big | |||
| DGX Station GB300 | 1.6-bit | 1M | 322 tok/s | 0.3 s |
| 8× H200 NVL | FP4 + FP8 | 1M | 135 tok/s | 0.1 s |
Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.
How to run it
- llama.cpp
llama-server -hf unsloth/DeepSeek-V4.1-Flash-1017-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-V4.1-Flash- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V4.1-Flash-MLX-4bit
Questions
How much VRAM does DeepSeek V4.1 Flash need?
DeepSeek V4.1 Flash needs 431 GB for its weights at 4-bit, 432 GB with an 8K context and 432 GB with 32K.
Can DeepSeek V4.1 Flash run on an RTX 4090?
Not on one card. The smallest machine here that runs it is the M3 Ultra 256 GB.