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 R1 Distill Llama 8B Abliterated
DeepSeek · maicog
Params8.03B
Context128K
Smallest4.7 GB
ReasoningTool use
DE
DeepSeek R1 Llama 8B F32
DeepSeek · prithivMLmods
Params8B
Context—
Smallest15.6 GB
Reasoning
DE
Qwen Deepseek V2.1
DeepSeek · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
Tool use
DE
BioThoughts DeepSeek 8B
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
ahmedheakl asm2asm deepseek 1.3b 100k x86 O0 2ep arm gnueabi gcc
DeepSeek · RichardErkhov
Params1.35B
Context16K
Q4_K_M0.9 GB
GGUF
DE
FuseO1 DeepSeekR1 QwQ SkyT1 32B Preview
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
DeepSeek-R1-Distill-Qwen-14B-GSPO-Easy
DeepSeek · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 70B
DeepSeek · thisnick
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
DE
RASA All3 DeepSeek V2 Lite Chat
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
GGUF
DE
RTLCoder Deepseek v1.1
DeepSeek · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
Coding
DE
LlamaAligned DeepSeekR1 Distill 70b
DeepSeek · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
DE
DeepSeek SQL Expert
DeepSeek · ukung
Params1.35B
Context16K
Q4_K_M0.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen2.5 1.5B LimaRP Uncensored Q5 K M
DeepSeek · Novaciano
Params1.78B
Context128K
Smallest1.3 GB
ReasoningRoleplayTool use
DE
Deepseek ai.DeepSeek R1 Distill Qwen 32B
DeepSeek · DevQuasar-5
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
Deepseek Coder 1.3b Instruct
DeepSeek · raghav0
Params1.35B
Context16K
Q4_K_M0.9 GB
Coding
DE
Llama 3.1 8B DeepSeek67B Distilled
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
DE
Qwen2.5 MOE 2X1.5B DeepSeek Uncensored Censored 4B
DeepSeek · matrixportalx
Params4.09B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
DE
ThinkEdit deepseek qwen 1.5b
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
BokantLM0.1 135M Deepseek
DeepSeek · mradermacher
Params135M
Context8K
Q4_K_M0.1 GB
Reasoning
DE
DeepSeek-R1-Distill-Qwen-1.5B-S-2
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
SAND MathScience DeepSeek Qwen32B
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
DeepSeek V4 Flash
DeepSeek · hampsonw
Params284B
Context1024K
Smallest86.7 GB
ReasoningTool use
DE
deepseek Kunoichi DPO
DeepSeek · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · pbatra
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
DeepSeek R1 0528 Qwen3 8B KAYLA BASE3
DeepSeek · mradermacher
Params8.19B
Context500K
Q4_K_M5.0 GB
ReasoningTool use
DE
Qwen2.5 1.5B Instruct
DeepSeek · pravdin
Params1.78B
Context32K
Q4_K_M1.1 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · roleplaiapp
Params1.78B
Context128K
Smallest1.3 GB
CodingReasoningRoleplay
DE
deepseek r1 llama 8b harmony i1
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
Llama 3.3 70b DeepSeek R1 Dropable V1.01
DeepSeek · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use

Keep browsing