RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run DeepSeek V4 Flash Vision Exp locally?

DeepSeek V4 Flash Vision Exp by deepseek-ai has 305B parameters (15B active per token, 256 experts, 6 used per token). At 4-bit with an 8K context it needs about 175 GB of GPU memory. It fits on 6 of 65 GPUs and Macs we track.

175 GBQ4_K_M · 8K context
nonesmallest consumer GPU that fits
M3 Ultra 512GBsmallest Mac that fits
1Mmax context
GQAattention type

GGUF quant file sizes were not in size order, so this page uses size estimates instead of real file sizes.

This model uses a newer compressed or sparse attention design. Our KV-cache numbers use the standard formula, so treat long-context figures as an upper bound.

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K)rough107 GB108 GB110 GB119 GB
3-bit (Q3_K_M)usable140 GB140 GB142 GB151 GB
4-bit (Q4_K_M)good, most popular174 GB175 GB177 GB186 GB
5-bit (Q5_K_M)very good203 GB204 GB206 GB215 GB
6-bit (Q6_K)near lossless234 GB234 GB236 GB245 GB
8-bit (Q8_0)effectively lossless302 GB303 GB305 GB314 GB
16-bit (F16/BF16)original weights568 GB569 GB571 GB580 GB

Which GPUs and Macs run DeepSeek V4 Flash Vision Exp?

Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)
RTX 3060 12GB12 GBNo———details
RTX 4060 Ti 16GB16 GBNo———details
RTX 309024 GBNo———details
RTX 409024 GBNo———details
RTX 509032 GBNo———details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBNo———details
Mac M4 Pro 48GB48 GBNo———details
Mac M4 Max 128GB128 GBNo———details
Mac M3 Ultra 512GB512 GBFitsQ8_0303 GB51details
DGX Spark128 GBTightQ2_K108 GB48details
RTX 407012 GBNo———details
RTX 5060 Ti 16GB16 GBNo———details
RTX 40608 GBNo———details
Arc B58012 GBNo———details
RTX 3060 Ti8 GBNo———details
RTX 30708 GBNo———details
RTX 3080 10GB10 GBNo———details
RTX 3080 12GB12 GBNo———details
RTX 3090 Ti24 GBNo———details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBNo———details
RTX 4070 Ti12 GBNo———details
RTX 4070 Ti Super16 GBNo———details
RTX 408016 GBNo———details
RTX 4080 Super16 GBNo———details
RTX 50608 GBNo———details
RTX 507012 GBNo———details
RTX 508016 GBNo———details
2x RTX 30902×24 GBNo———details
2x RTX 40902×24 GBNo———details
2x RTX 50902×32 GBNo———details
RTX A600048 GBNo———details
RTX 6000 Ada48 GBNo———details
RTX PRO 6000 Blackwell96 GBNo———details
L40S48 GBNo———details
A100 40GB40 GBNo———details
A100 80GB80 GBNo———details
H100 PCIe80 GBNo———details
H100 SXM80 GBNo———details
H200141 GBFitsQ2_K108 GB840details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBNo———details
RX 7900 GRE16 GBNo———details
RX 7900 XT20 GBNo———details
RX 907016 GBNo———details
RX 9070 XT16 GBNo———details
Ryzen AI Max+ 395 128GB128 GBTightQ2_K108 GB45details
Arc A770 16GB16 GBNo———details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBNo———details
Mac M3 24GB24 GBNo———details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBNo———details
Mac M1 Pro 32GB32 GBNo———details
Mac M3 Pro 36GB36 GBNo———details
Mac M4 Pro 24GB24 GBNo———details
Mac M4 Pro 64GB64 GBNo———details
Mac M1 Max 64GB64 GBNo———details
Mac M2 Max 96GB96 GBNo———details
Mac M3 Max 128GB128 GBNo———details
Mac M4 Max 64GB64 GBNo———details
Mac M2 Ultra 192GB192 GBFitsQ2_K108 GB140details
Mac M3 Ultra 256GB256 GBFitsQ3_K_M140 GB110details

Prefer an API?

DeepSeek: DeepSeek V4 Flash Vision Exp is on OpenRouter at $0.44 per 1M input tokens and $1.32 per 1M output tokens. Price details and history →

Questions

How much VRAM does DeepSeek V4 Flash Vision Exp need?

About 175 GB at 4-bit (Q4_K_M) with an 8K context: 173 GB of weights (estimated), 0.8 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 303 GB.

What is the smallest GPU that runs DeepSeek V4 Flash Vision Exp?

No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the Mac M3 Ultra 512GB (512 GB).

Can I run DeepSeek V4 Flash Vision Exp on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M3 Ultra 512GB or larger, using the default macOS GPU memory limit.

Similar models

Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.

DeepSeek V4 Flash 0731

304B · 175 GB at 4-bit

DeepSeek V4 Flash DSpark

304B · 175 GB at 4-bit

DeepSeek V4 Flash

291B · 167 GB at 4-bit

MiMo V2 Flash

310B · 176 GB at 4-bit

Hy3

299B · 173 GB at 4-bit

Hy3 preview

299B · 173 GB at 4-bit

Model facts

Hugging Face repodeepseek-ai/DeepSeek-V4-Flash-Vision-Exp
Parameters304,646,824,126 (305B) · ~15B active (computed from config)
Layers / hidden size43 / 4096
AttentionGQA; 64 heads, 1 KV heads, head dim 512
KV cache per token (FP16)96.8 KiB
Max context1,048,576 tokens
Licensemit
Released on HFAug 31, 2026
Downloads (30d) / likes36,166 / 970

Sources: Hugging Face model API · config.json (deepseek-ai/DeepSeek-V4-Flash-Vision-Exp) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.