How much memory does DeepSeek V4 Flash need?
About 179 GB at Q4_K_M with an 8K context. It runs on a Mac with 256 GB of unified memory or more.
Try other settings in the calculatorMemory by quantization and context
Total memory: weights, KV cache in F16 and about 1 GB of buffers. Under each total, the smallest Mac that can run it with the default GPU memory limit.
| Quantization | 8K context | 32K context | 128K context |
|---|---|---|---|
| Q3_K_M | 143 GB192 GB Mac | 143 GB192 GB Mac | 144 GB192 GB Mac |
| Q4_K_M | 179 GB256 GB Mac | 179 GB256 GB Mac | 180 GB256 GB Mac |
| Q5_K_M | 208 GBtoo big for a Mac | 208 GBtoo big for a Mac | 209 GBtoo big for a Mac |
| Q6_K | 240 GBtoo big for a Mac | 240 GBtoo big for a Mac | 240 GBtoo big for a Mac |
| Q8_0 | 310 GBtoo big for a Mac | 310 GBtoo big for a Mac | 311 GBtoo big for a Mac |
| F16 | 583 GBtoo big for a Mac | 583 GBtoo big for a Mac | 584 GBtoo big for a Mac |
About the model
- Parameters
- 291B
- Type
- Mixture of experts, 256 experts
- Attention
- compressed sparse attention
- KV cache, F16
- 0.0 GB at 8K, 0.7 GB at 128K
- On Hugging Face
- deepseek-ai/DeepSeek-V4-Flash
Most layers store their cache only every few tokens or keep a short window, so the KV cache is a fraction of what a standard model would need. As a mixture-of-experts model it loads every expert into memory, so memory follows the total parameter count, while speed follows the smaller number of active parameters.
Questions
How much memory does DeepSeek V4 Flash need?
About 179 GB at Q4_K_M with an 8K context: 178 GB of weights, 0.0 GB of KV cache and about 1 GB of buffers. At 32K context it needs about 179 GB.
Can DeepSeek V4 Flash run on a Mac?
Yes. At Q4_K_M with an 8K context it fits on a Mac with 256 GB of unified memory or more, using the default GPU memory limit of about three quarters.
How big is the DeepSeek V4 Flash KV cache?
About 0.0 GB at 8K tokens and 0.7 GB at 128K tokens with an F16 cache. Its attention design: compressed sparse attention.
Other models
- Gemma 4 12B
- gpt-oss 20B
- Gemma 4 26B-A4B
- Qwen3.8 27B
- GLM-4.7 Flash
- Gemma 4 31B
- Qwen3.6 35B-A3B
- gpt-oss 120B
- Mistral Medium 3.5
- Qwen3.8 Flash Next
- GLM-5.3
- DeepSeek V4 Pro
- Kimi K3
Data read from Hugging Face on 2026-11-09. These are estimates; benchmarks on this site report measured memory. How the estimate works. Compare all models in the model fit chart.
Get the next one
New benchmarks and agent runs by email, with the raw data. Or follow on RSS or X.