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 Qwen 32B GuiyangGuian Lora v1
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
Deepseek Coder 1.3B Kexer
DeepSeek · mradermacher
Params1.35B
Context16K
Q4_K_M0.9 GB
Coding
DE
Qwen2.5 32B
DeepSeek · viwo50
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
deepseek math 7b rl
DeepSeek · mzwing
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
DE
Deepseek ai.DeepSeek V3 Base Bf16
DeepSeek · DevQuasar-3
Params671B
Context160K
Smallest244.0 GB
Tool use
DE
Phi 4 Deepseek R1K RL EZO
DeepSeek · mradermacher
Params14.7B
Context16K
Q4_K_M9.1 GB
GGUF
DE
Srijith rkr deepseek base 1e 4 NO cot speed incorrect samples 5 epoch
DeepSeek · RichardErkhov
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · NonMiFrega
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
Srijith rkr deepseek base 1e 4 NO cot only speed samples 5 epoch
DeepSeek · RichardErkhov
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
DE
ThinkEdit deepseek qwen 1.5b i1
DeepSeek · mradermacher
Params1.78B
Context128K
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 14B Japanese
DeepSeek · bluepen5805
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · xiaozhibro
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · John1604
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
deepseek ai.DeepSeek V4 Flash Vision Exp
DeepSeek · DevQuasar
Params284B
Context1024K
Smallest103.1 GB
GGUF
DE
Qwen2.5 0.5B
DeepSeek · tensorblock
Params494M
Context32K
Smallest0.3 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · EasierAI
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
CoderO1 DeepSeekR1 Coder 32B Preview
DeepSeek · RDson
Params32.8B
Context128K
Q4_K_M19.9 GB
CodingTool use
DE
LFM2.5 1.2B MEGABRAIN Thinking Claude Polaris Deepseek GLM Abliterated Failspy
DeepSeek · mradermacher
Params1.17B
Context125K
Q4_K_M0.7 GB
ReasoningTool use
DE
Deepseek Light Novel Translator 1
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
Srijith rkr deepseek base 1e 4 NO cot speed incorrect samples 10 epoch
DeepSeek · RichardErkhov
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
DE
deepseek law v3
DeepSeek · Danielrahmai1991
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 32B Abliterated v2
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
Sakura DeepSeek V4.1 Flash 1017 Maya S IQ2 XXS Engram Q3 K
DeepSeek · webmp3
Params748B
Context1024K
Smallest262.7 GB
GGUF
DE
Deepseek Ai DeepSeek Coder V2 Lite Instruct
DeepSeek · tensorblock
Params15.7B
Context160K
Smallest6.4 GB
Coding
DE
suayptalha.DeepSeek R1 Distill Llama 3B
DeepSeek · DevQuasar-9
Params3.21B
Context128K
Q4_K_M2.0 GB
Reasoning
DE
DeepSeek R1 Distill Llama 8B Instruct bnb 4bit medical
DeepSeek · jiaqi123abc
Params8.03B
Context128K
Q4_K_M0.9 GB
ReasoningTool use
DE
DeepSeek Coder V2 Lite Instruct
DeepSeek · q10108158
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · 1bit-MONSTER
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · John1604
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use

Keep browsing