OpenModelsHQ

DeepSeek-V4-Flash-Vision-Exp

DeepSeekVisionMoEMITChina Desk

DeepSeek-V4-Flash-Vision-Exp is an open-weight vision and language model from DeepSeek with 305B parameters (mixture of experts). At 4-bit it needs about 201.9 GB of memory, so the smallest device in our directory that fits it is the Rubin, which is announced but not shipping yet.

Overview

Estimated memory at 4-bit
201.9GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
305B
Mixture of experts, all weights counted
Context window
1024K
1,048,576 tokens
Cheapest API, blended / 1M
$0.3234
₹30 · DeepInfra · 3:1 input to output
All DeepSeek API prices

Key information

Lab
DeepSeek
Released
31 Aug 2026
Parameters
305B · MoE
Type
Vision and language
Context
1,048,576 tokens
License
MIT
HF downloads, 30 days
138,190
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
DeepSeek-V4-Flash-Vision-Exp needs about 201.9 GB at 4-bit, 356 GB at 8-bit and 671 GB at 16-bit. At 4-bit it fits none of the reference devices. Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q4201.9 GB
Q8356 GB
BF16671 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 201.9 GBToo big 561%RubinAnnounced288 GB memory
8-bit (Q8)≈ 356 GBToo big 989%No single device in our directory has enough memory
16-bit (BF16)≈ 671 GBToo big 1864%No single device in our directory has enough memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

mlx-community/DeepSeek-V4-Flash-Vision-Exp-MLXCheck your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUFFind compatible hardware

Through an API

DeepInfra (fp8) is the cheapest provider we found.

$0.2156 / $0.6468

Input / output per 1M tokens
₹20 / ₹61 at ₹94.29 per $1

Blended: $0.3234 (₹30) per 1M. Ranked by a 3:1 mix of input and output tokens.

MLX on Apple SiliconView repository
mlx_vlm.generate --model mlx-community/DeepSeek-V4-Flash-Vision-Exp-MLX \
  --prompt "Describe this image." --image image.jpg
GGUF with llama.cppView repository
llama-cli -hf unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.

Hosted API 2

USD and INR per million tokensAll DeepSeek API prices
Precision
DeepInfraCheapest$0.3234₹30$0.2156₹20$0.6468₹611,048,576FP8
GMICloud$0.66₹62$0.44₹41$1.32₹1241,048,575FP8
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does DeepSeek-V4-Flash-Vision-Exp need? At an 8k context, about 201.9 GB at 4-bit, 356 GB at 8-bit and 671 GB at 16-bit (BF16). A longer context needs more.

Can I run DeepSeek-V4-Flash-Vision-Exp on a Mac? No current Mac fits the 4-bit estimate of 201.9 GB. The smallest Mac in our directory that does is the Mac Studio M3 Ultra (512GB), which is discontinued. An MLX build is available: mlx-community/DeepSeek-V4-Flash-Vision-Exp-MLX.

Does the full context fit? DeepSeek-V4-Flash-Vision-Exp supports up to 1,048,576 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is DeepInfra, at $0.22 per 1M input tokens and $0.65 per 1M output tokens (₹20 and ₹61 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

MIT. This license permits commercial use, modification and redistribution, as long as the copyright and license notice are kept. This summary is not legal advice.

Read MIT

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources