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
LL
Llama 3.2 SUN HDIC 1B Instruct
Llama · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
ReasoningTool use
MO
Moonshine Base (Arabic)
Moonshine · handy-computer
Params62M
Context—
Smallest0.1 GB
GGUF
QW
Qwen3.5 2B EmperoAI Qwen3.8 Distill Heretic Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
MO
moonshine base zh
Moonshine · handy-computer
Params62M
Context—
Smallest0.1 GB
GGUF
PA
parakeet tdt ctc 1.1b
Parakeet · cstr
Params1.07B
Context—
Smallest0.7 GB
GGUF
TI
TinyMistral 248M v2.5 Instruct
Tinymistral · MaziyarPanahi
Params248M
Context32K
Q4_K_M0.2 GB
Coding
IN
Internlm2 1_8b
InternLM · mradermacher
Params1.89B
Context32K
Q4_K_M1.2 GB
GGUF
GG
gguf pythia 1.4b sft full
Gguf · Felladrin
Params1.41B
Context2K
Q4_K_M0.9 GB
GGUF
QW
Qwen2.5 Math 1.5B Instruct
Qwen · lmstudio-community
Params1.54B
Context4K
Q4_K_M1.0 GB
GGUF
UD
Udgam-384M-Base-4K
Udgam · udgamlabs
Params384M
Context4K
Smallest0.4 GB
GGUF
DI
DialoGPT medium Loki
Dialogpt · QuantFactory
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
FI
FinMatcha 3B Instruct i1
Finmatcha · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LU
Lucy 128k
Lucy · bartowski
Params1.72B
Context128K
Q4_K_M1.1 GB
GGUF
QW
Qwen3.5 2B
Qwen · AaryanK
Params1.88B
Context256K
Q4_K_M1.3 GB
Vision
RE
reader lm 1.5b IMat
Reader · legraphista
Params1.54B
Context250K
Smallest0.4 GB
GGUF
QW
Qwen2 1.5b
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
GGUF
QW
Qwen3 4B Pingala8 2bit
Qwen · Genrius-AI
Params1.36B
Context40K
Smallest1.2 GB
ReasoningTool use
IN
Internvl3-1B-Instruct
Internvl · unsloth
Params630M
Context32K
Q4_K_M0.5 GB
CodingVision
SA
SatellaRAG 0.8B
Satellarag · mradermacher
Params773M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
SP
Spark X2.6 1.7B i
Spark · maternion
Params1.71B
Context1024K
Q4_K_M1.1 GB
ReasoningTool use
QW
Exe Guard Dynamic
Qwen · exe-ai-harness
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
LL
LlamaCorn 1.1B Chat
Llama · QuantFactory
Params1.1B
Context2K
Q4_K_M0.7 GB
Tool use
SA
Models Sail Sailor2 1B Chat
Sailor · MaziyarPanahi
Params988M
Context32K
Q4_K_M0.7 GB
GGUF
LL
Laravel 11 Llama 3.2 1B Instruct
Llama · yannelli
Params1.24B
Context128K
Q4_K_M0.8 GB
CodingTool use
RO
RORem mixed
Rorem · mayocream
Params2.57B
Context—
Smallest2.0 GB
GGUF
IN
Internlm2_5 1_8b
InternLM · mradermacher
Params1.89B
Context32K
Q4_K_M1.2 GB
GGUF
LL
Llama3.2 3B Esper2
Llama · QuantFactory
Params3.21B
Context128K
Q4_K_M2.0 GB
Coding
ST
HOT Step CPP StableStep
Stable · scragnog
Params1.45B
Context—
Q4_K_M0.8 GB
GGUF
SA
Sailor-1.8B-Chat
Sailor · mradermacher
Params1.84B
Context32K
Q4_K_M1.2 GB
GGUF
OP
OpenELM 1_1B
Openelm · mradermacher
Params1.08B
Context2K
Q4_K_M0.7 GB
GGUF

Other sizes

Keep browsing