LLMs ·

DeepSeek V4.1 Flash (552B-A16B)

Parameters
763B (16.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
mit
Released
2026-09

How to run it

Ollama

Ollama offers this only as a cloud model (it runs on Ollama’s servers, not your machine). To run it locally, use the original weights from Hugging Face.

Original weights · Hugging Face

Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.

huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run DeepSeek V4.1 Flash (552B-A16B)

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

Docker Model Runner

Handy if you already work in Docker.

Also good:

App Type Opens it as Systems Engine Start
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve deepseek-ai/DeepSeek-V4.1-Flash
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V4.1-Flash
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

KV cache: compressed sparse KV cache shared across layers (4 source layers hold the global cache, about 890 bytes per token in FP4 on DeepSeek's runtime); estimate treats it like a latent cache.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 305 GB 306 GB 306 GB All files (opens in a new tab)
Q3_K_M Low 374 GB 375 GB 375 GB All files (opens in a new tab)
Q4_K_M Good 466 GB 466 GB 466 GB All files (opens in a new tab)
Q5_K_M High 542 GB 543 GB 543 GB All files (opens in a new tab)
Q6_K High 626 GB 626 GB 627 GB All files (opens in a new tab)
Q8_0 Very high 809 GB 810 GB 810 GB All files (opens in a new tab)
F16 Full 1,526 GB 1,527 GB 1,527 GB Original weights (opens in a new tab)

Best hardware for DeepSeek V4.1 Flash (552B-A16B)

Quality Hardware Quant Memory Speed Runs
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2025) (M4 Max or M3 Ultra)Apple M3 Ultra (512 GB) Q2_K 337 GB / 384 GB 69.5 tok/s Runs welltight fit
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (M5 Max or M5 Ultra)Apple M5 Ultra (512 GB) Q2_K 337 GB / 384 GB 92.5 tok/s Runs welltight fit
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. QNAP QAI-h1290FXAMD EPYC 7002 / 7003 series NAS (512 GB) Q3_K_M 412 GB / 471 GB 10.9 tok/s Runs welltight fit
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. QNAP TDS-h6889AXU-RPIntel Xeon Silver (4100 to 4300 series) NAS (512 GB) Q3_K_M 412 GB / 471 GB 5.4 tok/s Slowtight fit
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. QNAP TS-2888XIntel Xeon W-2100 series NAS (512 GB) Q3_K_M 412 GB / 471 GB 5.2 tok/s Slowtight fit
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. TerraMaster U8-725Intel Xeon D-2700 series NAS (512 GB) Q3_K_M 412 GB / 471 GB 4.0 tok/s Slowtight fit

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?