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 Flash 0731 Pruned 155B A13B
DeepSeek · takanori-ishikawa
Params155B
Context1024K
Smallest1.2 GB
GGUF
DE
FuseO1 DeepSeekR1 QwQ 32B Preview
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
deepseek math 7b instruct
DeepSeek · MaziyarPanahi
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
DE
Deepseek Llm 7b Chat
DeepSeek · matrixportalx
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
DE
DeepSeek-R1-Distill-Qwen-7B-GRPO
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 70B Uncensored v2 Unbiased
DeepSeek · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
DE
DeepSeek R1 Distill Llama 70B Uncensored
DeepSeek · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
DE
DeepSeek V4.1 Flash
DeepSeek · staccs
Params107B
Context1024K
Smallest103.4 GB
GGUF
DE
DeepSeek R1 ReDistill Qwen 1.5B v1.1
DeepSeek · ThomasBaruzier
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · PrunaAI
Params10M
Context128K
Q4_K_M0.0 GB
ReasoningTool use
DE
nsfw merge v4dot1 w deepseek ablit
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
DE
DeepSeek-R1-Distill-Qwen-14B
DeepSeek · Mungert
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
DE
DeepSeek V4 Flash DSpark drafter
DeepSeek · bleysg
Params19.8B
Context—
Smallest6.9 GB
GGUF
DE
Spiral DeepSeek R1 Distill Qwen 7B
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · NonMiFrega
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 8B Debiased
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 7B Abliterated
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 0528 Qwen3 8B KAYLA BASE2
DeepSeek · mradermacher
Params8.19B
Context500K
Q4_K_M5.0 GB
ReasoningTool use
DE
Nemotron Orchestrator 8B DeepSeek v3.2 Speciale Distill
DeepSeek · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · matrixportalx
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
deepseek-coder-7b-instruct-v1.5
DeepSeek · qwp4w3hyb
Params6.91B
Context4K
Q4_K_M4.2 GB
Coding
DE
DeepSeek R1 Distill Qwen 1.5B Abliterated
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 1.5B uncensored i1
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
Vietnamese 4B Chat
DeepSeek · N14QM
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningTool use
DE
Deepseek Coder 1.3b Base
DeepSeek · mradermacher
Params1.35B
Context16K
Q4_K_M0.9 GB
Coding
DE
DeepSeek-V2-Lite-Chat
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
GGUF
DE
Deepseek Math 7b Base
DeepSeek · mradermacher
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
DE
DeepSeek-R1-Distill-Llama-8B-Ablation
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
deepseek ai DeepSeek R1 Distill Llama 8B GGUF smashed
DeepSeek · PrunaAI
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
Llama 3 ThinkRoleplay DeepSeek R1 Distill 8B abliterated i1
DeepSeek · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
ReasoningRoleplay

Keep browsing