Tiny GGUF models

62726 GGUF models with 3B parameters or fewer. Sizes run from 1M to 3.5B parameters. The longest trained context is 795898K tokens.

Most downloadedNewestLargestLongest contextSmallest
MA
mamba 130m hf
Mamba · QuantFactory
Params129M
Context1024K
Q4_K_M0.1 GB
GGUF
GE
Gemma 2B Uncensored
Gemma · lemuralabs
Params2.51B
Context8K
Q4_K_M1.6 GB
Coding
QW
Qwen3.5 2B EmperoAI Qwen3.8 Distill Heretic Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
ED
vllm-d3-edge
Edge · ggml-org
Params748M
Context256K
Smallest0.8 GB
Vision
QW
Qwen3 1.7B
Qwen · gaianet
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
ST
stable code 3b
Stable · TheBloke
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
WE
WeVisOne VL 2B
Wevisone · mradermacher
Params2.03B
Context256K
Q4_K_M1.3 GB
Tool useVision
MI
MiniMax H3 Prompt Rewriter LoRA
Minimax · pytraveler
Params1.87B
Context—
Smallest2.0 GB
GGUF
MO
moss soundeffect
Moss · ilintar
Params1.49B
Context—
Smallest3.0 GB
GGUF
CO
Yi Coder 1.5B Chat
Coder · mradermacher
Params1.48B
Context128K
Q4_K_M1.0 GB
Coding
BG
bge m3
BGE · CompendiumLabs
Params567M
Context8K
Smallest1.2 GB
Embedding
MI
MiniCPM V 4.7 1B
MiniCPM · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
UN
unlimited ocr
Unlimited · vimalnakrani
Params2.93B
Context—
Q4_K_M2.0 GB
GGUF
ST
stable-code-3b
Stable · mradermacher
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
LI
LightOnOCR 3 0.8B
Lightonocr · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
Vision
MO
moss tts
Moss · ilintar
Params2.04B
Context—
Smallest4.1 GB
GGUF
QW
Qwen2.5 Coder 3B Instruct
Qwen · unsloth
Params3.09B
Context32K
Q4_K_M1.9 GB
Coding
MI
MiniCPM V 4.7 1B
MiniCPM · NANI-Nithin
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
MA
madlad400 3b mt
Madlad · jbochi
Params2.94B
Context—
Smallest1.0 GB
GGUF
UN
Unlimited OCR 2
Unlimited · AtomicChat
Params2.94B
Context128K
Smallest2.0 GB
Vision
RE
realvisxl v5.0
Realvisxl · off-grid-ai
Params3.47B
Context—
Smallest2.8 GB
GGUF
EM
embeddinggemma-2
Embeddinggemma · AtomicChat
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
EM
Embeddinggemma 300M Qat Q4_0 Unquantized
Embeddinggemma · ggml-org
Params303M
Context2K
Smallest0.3 GB
Embedding
JI
jina embeddings v2 base code
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
TI
Tiny Aya Global
Tiny · CohereLabs
Params3.35B
Context488K
Q4_K_M2.1 GB
GGUF
GL
GLM 5.3 Flash Uncensored Mixed Quant
GLM · Baekpica
Params564M
Context—
Smallest1.1 GB
GGUF
GE
Gemmasutra Mini 2B v1
Gemma · l3utterfly
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B Abliterated
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
LL
Llama3.2 DeepHermes 3 3B Preview Reasoning MAX NEO Imatrix
Llama · DavidAU
Params3.21B
Context128K
Q4_K_M2.5 GB
ReasoningRoleplayTool use
GR
Granite Speech 5.0 2b
Granite · ibm-granite
Params1.84B
Context16K
Q4_K_M1.1 GB
Vision

Other sizes

Keep browsing