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
CO
Yi Coder 1.5B Chat
Coder · mradermacher
Params1.48B
Context128K
Q4_K_M1.0 GB
Coding
SM
SmolLM2 1.7B Instruct Uncensored
SmolLM · mradermacher
Params1.81B
Context8K
Q4_K_M1.1 GB
GGUF
QW
Huihui Qwen3 1.7B Abliterated v2
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
OR
Ornith 1.0 35B MTP
Ornith · SC117
Params447M
Context256K
Smallest14.3 GB
ReasoningVision
PA
parakeet rnnt 0.6b
Parakeet · cstr
Params617M
Context—
Smallest0.4 GB
GGUF
JU
Juggernaut XL Ragnarok
Juggernaut · TinyRick1489
Params2.57B
Context—
Q4_K_M1.6 GB
GGUF
LF
LFM2.5-350M
Lfm · ensu-app
Params354M
Context125K
Q4_K_M0.2 GB
Tool use
AR
Armenian GPT 1.0 3B
Armenian · ArmGPT
Params3.43B
Context256K
Q4_K_M2.1 GB
Reasoning
QW
Qwen2.5 0.5B
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
LL
Llama 3.2 3B Instruct heretic
Llama · saidutta69
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
QW
Qwen2.5 0.5B Instruct
Qwen · second-state
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
DI
diar streaming sortformer 4spk v2.1
Diar · handy-computer
Params118M
Context—
Smallest0.1 GB
GGUF
MI
Ministral 3 3B Instruct 2512
Mistral · ggml-org
Params3.43B
Context256K
Smallest3.7 GB
Vision
QW
Models Qwen Qwen2.5 3B Instruct
Qwen · MaziyarPanahi
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
MI
Mistralai Shieldstral 1.0 3B
Mistral · Abiray
Params3.43B
Context256K
Q4_K_M2.1 GB
Vision
GE
Gemma 2 2b
Gemma · legraphista
Params2.61B
Context8K
Smallest0.8 GB
GGUF
PY
Pythia 2.8b Deduped
Pythia · mradermacher
Params2.78B
Context2K
Q4_K_M1.8 GB
GGUF
LL
Llama 3.2 3B Agent007 Coder
Llama · QuantFactory
Params3.21B
Context128K
Q4_K_M2.0 GB
Coding
QW
jinaai/test-qwen25-coder-jina-code-embeddings-1.5b
Qwen · jinaai
Params1.54B
Context32K
Smallest0.4 GB
CodingEmbedding
LL
Kiel 2.1 Sol
Llama · kiel2
Params3.2B
Context128K
Q4_K_M2.0 GB
GGUF
QW
Dolphin3.0 Qwen2.5 3B
Qwen · QuantFactory
Params3.4B
Context32K
Q4_K_M2.1 GB
CodingTool use
FU
Home FunctionGemma 270m
Functiongemma · acon96
Params268M
Context—
Smallest0.0 GB
GGUF
BG
bge-small-en-v1.5
BGE · ChristianAzinn
Params33M
Context512
Q4_K_M0.0 GB
Embedding
BO
Borealis 270m
Borealis · mradermacher
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
G9
G9v3 3B
NANI-Nithin
Params3B
Context128K
Q4_K_M1.8 GB
GGUF
HE
HelpingAI 3B coder
Helpingai · QuantFactory
Params3.48B
Context125K
Q4_K_M2.1 GB
Coding
QW
Qwen2.5 3B Instruct Heretic
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
ST
stable-code-instruct-3b
Stable · lmstudio-community
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
QW
Qwen3.6-35B-A3B
Qwen · AtomicChat
Params447M
Context256K
Smallest17.7 GB
Vision
QW
Replete LLM V2.5 Qwen 3b
Qwen · bartowski
Params3.4B
Context32K
Q4_K_M2.1 GB
GGUF

Other sizes

Keep browsing