antirez

deepseek v4.1 flash

deepseek v4.1 flash is a 754.6B mixture-of-experts deepseek41 model from antirez, with about 125.0B parameters active per token. Configured context length is 1,048,576 tokens. License: mit. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.

Parameters755B / 125B active

Context1024K

Attentiongqa

Licensemit

40 layers · 1 KV heads · head dim 512 · GGUF repo · config

Quant file sizes

Quant	File size	Source
Q8_0	746.7 GB	Estimated from parameters × bits per weight
Q6_K	576.3 GB	Estimated from parameters × bits per weight
Q5_K_M	500.8 GB	Estimated from parameters × bits per weight
Q4_K_M	426.1 GB	Estimated from parameters × bits per weight
Q3_K_M	342.6 GB	Estimated from parameters × bits per weight
Q2_K	294.3 GB	Estimated from parameters × bits per weight

On common machines

Device	Verdict	Quant	Speed
GeForce RTX 4060 Ti 8GB	Won't fit	Q2_K	—
GeForce RTX 3060 12GB	Won't fit	Q2_K	—
GeForce RTX 4060 Ti 16GB	Won't fit	Q2_K	—
GeForce RTX 4090	Won't fit	Q2_K	—
GeForce RTX 5090	Won't fit	Q2_K	—
Apple M4 Pro	Won't fit	Q2_K	—
Apple M5	Won't fit	Q2_K	—
CPU only · DDR5-5600	Won't fit	Q2_K	—

Smallest devices that fit it fully

No GPU or Mac in the catalog fits this model inside the default memory budget. A partial offload or a larger machine is required.

Run it

Commands for the GeForce RTX 4060 Ti 16GB estimate (Q2_K).

llama.cpp

# Quant size is estimated — the file may not be published yet
llama-server -hf antirez/deepseek-v4.1-flash-gguf:Q2_K -c 2048 -ngl 0

Ollama

ollama run deepseek-v4.1-flash

LM Studio

# Quant size is estimated — the file may not be published yet
lms get antirez/deepseek-v4.1-flash-gguf
# Then load quant Q2_K