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
QW
Qwen3.8 27B DFlash drafter bootstrap
Qwen · mrchuy
Params1.73B
Context256K
Smallest1.8 GB
GGUF
MI
Ministral 3B Heresy Unfiltered
Mistral · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
GGUF
ZO
zonos v0.1 transformer
Zonos · cstr
Params1.62B
Context—
Smallest0.0 GB
GGUF
ON
OneJev1.6 0.8B
Onejev · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
ST
sd3.5 large
Stable · gguf-org
Params695M
Context—
Smallest0.2 GB
GGUF
BI
Hy MT1.5 1.8B 1.25bit
Bit · AngelSlim
Params1.79B
Context—
Smallest0.5 GB
GGUF
QW
Qwen2.5 3B Instruct
Qwen · legraphista
Params3.09B
Context32K
Smallest0.8 GB
Tool use
LF
LFM2.5 Encoder 350M
Lfm · LiquidAI
Params354M
Context125K
Smallest0.2 GB
Coding
WE
WeVisOne VL
Wevisone · PALLER-NOVUS
Params407M
Context256K
Q4_K_M1.3 GB
Vision
SM
Biggie SmoLlm 0.4B
SmolLM · mradermacher
Params448M
Context2K
Q4_K_M0.3 GB
GGUF
FA
Falcon3 3B Base
Falcon · bartowski
Params3.23B
Context32K
Q4_K_M2.0 GB
GGUF
QW
Qwen3-1.7B
Qwen · XythicK
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
LL
AMD Llama 135m code
Llama · QuantFactory
Params134M
Context2K
Q4_K_M0.1 GB
Coding
LL
Llama Deepsync 3B
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
Coding
QW
Qwen2.5 1.5B
Qwen · QuantFactory
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
hydra nano git
Qwen · rahul05ranjan
Params752M
Context256K
Smallest0.8 GB
Tool use
LF
Lfm2-700M
Lfm · unsloth
Params742M
Context32K
Q4_K_M0.5 GB
GGUF
OP
OpenELM 3B
Openelm · mradermacher
Params3.04B
Context2K
Q4_K_M1.9 GB
GGUF
QW
Qwen2.5 Coder 1.5B Unsensored DPO
Qwen · Olak17
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
OP
OpenELM 270M Instruct
Openelm · mradermacher
Params272M
Context2K
Q4_K_M0.2 GB
GGUF
JI
jina embeddings v2 base es
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
LL
Llama Sentient 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
QW
Qwen3.5 0.8B
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
AY
Aya
Aya · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
LL
Llama 3.2 1b Uncensored RP Aesir
Llama · Novaciano
Params1.24B
Context128K
Smallest0.8 GB
Roleplay
WH
whisper small
Whisper · FL33TW00D-HF
Params242M
Context—
Smallest0.1 GB
GGUF
QW
Qwen3.8 2B Heretic Max
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
JI
jina embeddings v5 omni nano retrieval
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
EmbeddingVision
QW
qwen25 coder 3b uncensored
Qwen · tthanhannguyen
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision

Other sizes

Keep browsing