Skip to content
DeepSeek

DeepSeek R1

Maker’s page
Check price at Amazon for DeepSeek DeepSeek-R1 (affiliate link, opens in new tab)
Weights at 16-bit
1,342 GB
Weights at 8-bit (Q8_0)
713 GB
Weights at 4-bit (Q4_K_M)
407 GB
Smallest card at 4-bit
More than one card
Parameters
Active parameters
Layers
KV heads
Context
Licence

Specs

Active parameters
Attention heads
Context
Downloads (30 days)
Experts
Experts per token
Family
GGUF downloads
repobytesfilesquant
unsloth/DeepSeek-R1-GGUF140,231,438,4643 entriesUD-IQ1_S
unsloth/DeepSeek-R1-GGUF168,916,283,6484 entriesUD-IQ1_M
unsloth/DeepSeek-R1-GGUF196,162,482,4324 entriesUD-IQ2_XXS
unsloth/DeepSeek-R1-GGUF221,253,686,9445 entriesQ2_K_XS
unsloth/DeepSeek-R1-GGUF226,601,595,0405 entriesUD-Q2_K_XL
unsloth/DeepSeek-R1-GGUF244,028,343,9365 entriesQ2_K
unsloth/DeepSeek-R1-GGUF244,245,534,3365 entriesQ2_K_L
unsloth/DeepSeek-R1-GGUF319,198,395,7447 entriesQ3_K_M
unsloth/DeepSeek-R1-GGUF404,430,187,6169 entriesQ4_K_M
unsloth/DeepSeek-R1-GGUF475,396,558,14410 entriesQ5_K_M
unsloth/DeepSeek-R1-GGUF550,798,326,88012 entriesQ6_K
unsloth/DeepSeek-R1-GGUF713,286,514,36815 entriesQ8_0
unsloth/DeepSeek-R1-GGUF1,342,273,048,09630 entriesBF16
Hidden size
KV heads
KV latent rank (MLA)
Layers
Licence
Parameters
Parameters by type
Publisher
Released
RoPE key size (MLA)
Shared experts
Task

More from DeepSeek

Across the range 7 models by family