DeepSeek-V4-Flash
DeepSeek-V4-Flash by DeepSeek (284B parameters, MoE with 13B active per token). At Q4_K_M with an 8K context it needs about 168.9 GiB of memory. A 284B MoE with 13B active and a 1M-token context; at 4-bit it needs a 256 GB-class Mac. We can't model its compressed sparse attention yet, so our memory figures leave out the KV cache.
Last updated: 2026-10-13
Model facts
Memory needed
Weights + KV cache + runtime overhead, in GiB. Lower quantization = less memory, slightly lower quality.
| Quantization | 4K context | 8K context | 32K context |
|---|---|---|---|
| Q4_K_M | 168.9 GiB | 168.9 GiB | 168.9 GiB |
| Q5_K_M | 198.0 GiB | 198.0 GiB | 198.0 GiB |
| Q6_K | 229.3 GiB | 229.3 GiB | 229.3 GiB |
| Q8_0 | 295.6 GiB | 295.6 GiB | 295.6 GiB |
| FP16 | 555.9 GiB | 555.9 GiB | 555.9 GiB |
KV cache size unknown for this model
Which hardware runs it
Best quantization that fits each device with a 8K context. Estimates, not benchmarks. See the methodology.
Frequently asked questions
How much VRAM does DeepSeek-V4-Flash need?
With an 8K context, about 168.9 GiB at Q4_K_M and 295.6 GiB at Q8_0 (weights + KV cache + runtime overhead). Longer contexts need more memory for the KV cache.
Can DeepSeek-V4-Flash run on an GeForce RTX 4090?
DeepSeek-V4-Flash does not fit on the GeForce RTX 4090 (24 GB), even at Q4_K_M with an 8K context.
Can I run DeepSeek-V4-Flash on a Mac?
Yes. DeepSeek-V4-Flash fits on the M3 Ultra (256 GB) at Q4_K_M with an 8K context, using about 168.9 GiB, at an estimated 68 tokens/s.
Can DeepSeek-V4-Flash be used commercially?
DeepSeek-V4-Flash is released under MIT. The licence allows commercial use (read its conditions).