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 Pro Qwen3.5 4B
DeepSeek · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningVision
DE
Deepseek ai.DeepSeek V3.2 BF16
DeepSeek · DevQuasar
Params670B
Context160K
Q4_K_M404.5 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · second-state
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
DE
OREAL DeepSeek R1 Distill Qwen 7B
DeepSeek · lmstudio-community
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
DE
DeepSeek R1
DeepSeek · bartowski
Params671B
Context160K
Q4_K_M404.4 GB
Reasoning
DE
DeepSeek V4.1 Flash 1017 IQ2 XXS
DeepSeek · acrogenesis
Params748B
Context1024K
Smallest359.3 GB
GGUF
DE
ultratensor models
DeepSeek · NagusameCS
Params73.8B
Context1024K
Smallest17.1 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Base
DeepSeek · bartowski
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
DE
Andy 3.5
DeepSeek · Sweaterdog
Params7.62B
Context128K
Q4_K_M1.1 GB
Reasoning
DE
Qwen2.5 MOE 2X7B DeepSeek Abliterated UNCensored 19B i1
DeepSeek · mradermacher
Params19B
Context128K
Q4_K_M11.6 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 7B Abliterated Obliteratus
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
DE
Llama 3.1 TAIDE R1 8B Chat
DeepSeek · voidful
Params8.52B
Context128K
Smallest17.1 GB
Reasoning
DE
deepseek coder 6.7B kexer
DeepSeek · QuantFactory
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
DE
DeepSeek V4.1 Flash
DeepSeek · mxxm-t
Params748B
Context1024K
Smallest8.0 GB
GGUF
DE
DeepSeek-V2-Lite
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
GGUF
DE
DeepSeek R1 Distill Qwen 14B
DeepSeek · second-state
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
DE
DeepSeek V2.5 1210
DeepSeek · bartowski
Params236B
Context160K
Q4_K_M142.5 GB
GGUF
DE
DeepSeek OCR
DeepSeek · sabafallah
Params2.93B
Context—
Q4_K_M2.0 GB
GGUF
DE
Deepseek-Prover-V2-671B-Bf16
DeepSeek · unsloth
Params671B
Context160K
Q4_K_M404.5 GB
Coding
DE
Qwen2.5 32B
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
DE
deepseek coder v2 lite instruct
DeepSeek · mad-lab-ai
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
DE
DeepSeek-Coder-V2-Lite-Base
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · roleplaiapp
Params7.62B
Context128K
Q4_K_M4.7 GB
CodingReasoningRoleplay
DE
DeepSeek R1 Distill Qwen 32B Uncensored
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.8 GB
Reasoning
DE
DeepSeek V4.1 Flash 1017 GSQ RCO
DeepSeek · taurusduan
Params197B
Context—
Smallest110.6 GB
GGUF
DE
DeepSeek V4 Flash 0731 MXFP4 Q3 K Q2 K mixed
DeepSeek · BahamutRU
Params284B
Context—
Smallest126.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B Fully Uncensored
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
DE
DeepSeek V4.1 Flash 1017 VQ
DeepSeek · Baekpica
Params485M
Context—
Smallest1.0 GB
GGUF
DE
DeepSeek V4.1 Flash 1017 GSQ RCO StrixHalo
DeepSeek · Harsha001
Params658B
Context1024K
Smallest214.8 GB
ReasoningTool use

Keep browsing