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 Power Qwen 1B
DeepSeek · wan202101
Params1.78B
Context128K
Smallest1.9 GB
ReasoningTool use
DE
DeepSeek R1 0528 Qwen3 11B
DeepSeek · mradermacher
Params10.5B
Context128K
Q4_K_M6.4 GB
ReasoningTool use
DE
DeepSeek V4.1 Flash 1017 DSpark FLE
DeepSeek · sirfyyn
Params14.2B
Context1024K
Smallest5.2 GB
GGUF
DE
nsfw merge v4dot1 w deepseek ablit i1
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
DE
DeepSeek R1 Rafayel 14B V1
DeepSeek · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 32B Heretic
DeepSeek · fairy322
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
CodeFuse DeepSeek 33B iMat
DeepSeek · dranger003
Params33.3B
Context16K
Smallest12.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · DheyoAI
Params1.78B
Context128K
Smallest1.7 GB
ReasoningTool use
DE
DeepSeek V4.1 Flash GSQ Uncensored
DeepSeek · robertbschuette
Params14.7B
Context—
Smallest5.7 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · ggml-org
Params32.8B
Context128K
Smallest34.8 GB
ReasoningTool use
DE
Deepseek R1 1.5b Heretic
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
deepseek r1 distill qwen 1.5 unsloth sft python q4 k m
DeepSeek · sdiazlor
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
DE
deepseek r1 0528 distilled qwen3
DeepSeek · ertghiu256
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 7B Desyced
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 0528 CODER DRAFT 0.6B v1.1
DeepSeek · mradermacher
Params590M
Context64K
Q4_K_M0.5 GB
CodingReasoningTool use
DE
yujiepan deepseek v3 tiny random
DeepSeek · RichardErkhov
Params9M
Context—
Q4_K_M0.0 GB
GGUF
DE
LFM2.5 1.2B MEGABRAIN Thinking Polaris ClaudeHOPUS Deepseek GLM
DeepSeek · mradermacher
Params1.17B
Context125K
Q4_K_M0.7 GB
ReasoningTool use
DE
Qwen3.5 2b Glm Deepseek Distillation
DeepSeek · ertghiu256
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
DE
CoderO1 DeepSeekR1 Coder 32B Preview
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
CodingTool use
DE
Deepseek Paraphrase
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · DuoNeural
Params1.78B
Context128K
Smallest0.8 GB
ReasoningTool use
DE
DeepSeek R1 8B FT medical o1 reasoning SFT
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
Deepseek Ai Deepseek Coder 33b Base
DeepSeek · tensorblock
Params33.3B
Context16K
Smallest12.4 GB
Coding
DE
DeepSeek V4.1 Flash 1017 V3 320 IQ1S
DeepSeek · cliecy
Params658B
Context1024K
Smallest206.1 GB
GGUF
DE
DeepSeek-R1-0528-Qwen3-8B
DeepSeek · Mungert
Params8.19B
Context128K
Q4_K_M5.2 GB
ReasoningTool use
DE
deepseek coder 1.3b typescript
DeepSeek · keriati
Params1.35B
Context16K
Smallest1.0 GB
Coding
DE
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
DeepSeek · featherless-ai-quants
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · osllmai-community
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 8B Ko Reasoning
DeepSeek · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
DE
Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Reasoning

Keep browsing