DeepSeek GGUF models

4419 GGUF models in the DeepSeek family, quantized by 1572 uploaders. Sizes run from 1M to 5376B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
DE
DeepSeek V4.1 Flash 1017 GSQ RCO
DeepSeek · ISTA-DASLab
Params197B
Context—
Smallest110.6 GB
GGUF
DE
DeepSeek V4.1 Flash Vision Encoder
DeepSeek · antirez
Params1400B
Context—
Smallest1.0 GB
GGUF
DE
Huihui DeepSeek V4 Flash 0731 abliterated
DeepSeek · huihui-ai
Params10B
Context—
Smallest10.9 GB
GGUF
DE
Huihui DeepSeek V4 Flash abliterated ds4
DeepSeek · huihui-ai
Params50B
Context—
Smallest3.8 GB
GGUF
DE
DeepSeek V4.1 Flash 1017
DeepSeek · unsloth
Params748B
Context1024K
Smallest8.0 GB
GGUF
DE
DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO IQ2 XXS
DeepSeek · Abiray
Params197B
Context—
Smallest110.6 GB
GGUF
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · unsloth
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
DE
DeepSeek V4 Flash 0731
DeepSeek · unsloth
Params284B
Context—
Smallest10.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
DE
DeepSeek V4.1 Flash 1017 Maya
DeepSeek · peasantsmith
Params748B
Context—
Smallest276.6 GB
GGUF
DE
DeepSeek V4.1 Flash 1017 ds4
DeepSeek · nazeshinjite
Params755B
Context—
Smallest1.0 GB
GGUF
DE
Deepseek-R1-Distill-Qwen-1.5B
DeepSeek · unsloth
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
DE
DeepSeek-V4-Pro-0813
DeepSeek · unsloth
Params1570B
Context1024K
Smallest849.7 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
DE
DeepSeek V4.1 Flash GSQ RCO
DeepSeek · pfeifferj
Params748B
Context—
Smallest9.3 GB
GGUF
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · unsloth
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
DE
DeepSeek R1 Distill Qwen 14B
DeepSeek · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
DE
DeepSeek V4.1 Flash
DeepSeek · audreyt
Params755B
Context—
Smallest365.7 GB
GGUF
DE
DeepSeek V4.1 Flash 1017 Vision Encoder
DeepSeek · kyuz0
Params755B
Context—
Smallest1.0 GB
GGUF
DE
DeepSeek V4.1 Flash UNCENSORED DwarfStar Q2
DeepSeek · pyrodog
Params490M
Context—
Smallest1.0 GB
GGUF
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · lmstudio-community
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · bartowski
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
DE
Deepseek-R1-Distill-Llama-8B
DeepSeek · unsloth
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
DE
DeepSeek R1 Distill Qwen 14B
DeepSeek · unsloth
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
DE
deepseek-ai_deepseek-coder-6.7b-instruct
DeepSeek · TheBloke
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
DE
Models Deepseek Ai DeepSeek R1 0528 Qwen3 8B
DeepSeek · MaziyarPanahi
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
DE
Deepseek-R1-Distill-Llama-70B
DeepSeek · unsloth
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
DE
DeepSeek V3 0324
DeepSeek · MaziyarPanahi
Params671B
Context160K
Smallest133.6 GB
GGUF
DE
DeepSeek V4.1 Flash UNCENSORED
DeepSeek · Adolphsson
Params748B
Context—
Q4_K_M426.1 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · bartowski
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning

About the DeepSeek GGUF models

DeepSeek is represented on ggufmodels.com by 4,419 GGUF models, quantized by 1,572 uploaders on Hugging Face. The most downloaded are DeepSeek V4.1 Flash 1017 GSQ RCO, DeepSeek V4.1 Flash Vision Encoder and Huihui DeepSeek V4 Flash 0731 abliterated. Parameter counts run from 1M to 5376B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a DeepSeek model is between 0.0 to 954.6 GB, which is the quant most people start with. Most files come from mradermacher (955), roleplaiapp (222) and Thireus (165). The quants you will meet most often are Q4_K_M (2356), Q8_0 (1841), Q5_K_M (1587) and Q2_K (1574), where the number is how many models offer that quant.

Frequently asked questions

Which DeepSeek GGUF should I download?

The most downloaded DeepSeek GGUF here is DeepSeek V4.1 Flash 1017 GSQ RCO. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a DeepSeek model need?

Q4_K_M files of DeepSeek models on this site range from 0.0 to 954.6 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do DeepSeek GGUF files come from?

The most common quantizers here are mradermacher, roleplaiapp and Thireus. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing