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
SL
slim summary tool
Slim · llmware
Params2.8B
Context4K
Smallest1.7 GB
Tool use
IN
Internlm2_5 1_8b Chat
InternLM · mradermacher
Params1.89B
Context32K
Q4_K_M1.2 GB
GGUF
SM
gguf SmolLM 135M Instruct
SmolLM · Felladrin
Params135M
Context2K
Smallest0.1 GB
GGUF
QW
Qwen 3.5 2b Roleplay Tuned
Qwen · mradermacher
Params1.94B
Context256K
Q4_K_M1.3 GB
ReasoningRoleplayTool use
MI
CherryPit 1.1 2B
MiniCPM · DRUPEs
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingReasoningTool use
ER
ERNIE Image Abliterated
Ernie · ponpoke
Params3.43B
Context256K
Q4_K_M2.1 GB
GGUF
IL
Illustrious XL v2.0
Illustrious · btaskel
Params2.57B
Context—
Smallest2.8 GB
GGUF
QW
Huihui Qwen3 0.6B Abliterated v2
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
NO
Nova-1.2-0.8B
Nova · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool use
QW
qwen3 5 2b q4 k m ggml llama cpp vivo x300
Qwen · Arm
Params1.88B
Context256K
Smallest1.3 GB
Vision
MO
MobileVLM V2 1.7B
Mobilevlm · ZiangWu
Params1.36B
Context2K
Smallest0.8 GB
Vision
QW
Qwen2.5 Math 1.5B
Qwen · QuantFactory
Params1.54B
Context4K
Q4_K_M1.0 GB
Tool use
HA
Haas-ja-v1.0
Haas · sakasegawa
Params616M
Context—
Smallest0.4 GB
GGUF
LL
Llama 3.2 3B Instruct Heretic Ablitered Uncensored
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
QW
Qwen2.5 Math 1.5B Instruct
Qwen · second-state
Params1.54B
Context4K
Q4_K_M1.0 GB
CodingTool use
LF
Lfm2-2.6B-Exp
Lfm · unsloth
Params2.57B
Context125K
Q4_K_M1.6 GB
Tool use
QW
Qwen3-1.7B-abliterated
Qwen · Mungert
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
DO
Doctor-Chad
Doctor · mradermacher
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
MI
Mistral Large 4 1T A52B Uncensored
Mistral · AtomicChat
Params114M
Context—
Smallest0.5 GB
GGUF
VI
vinallama-2.7b
Vinallama · RichardErkhov
Params2.77B
Context4K
Q4_K_M1.7 GB
GGUF
KU
KURE v1
Kure · mykor
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
QW
Qwopus3.5 9B Coder MTP
Qwopus · noctrex
Params1M
Context—
Smallest0.0 GB
GGUF
BA
bananamind tts
Bananamind · cstr
Params13M
Context—
Smallest0.0 GB
GGUF
MI
minicpm5 1B GLM 5.2 Agentic v9
MiniCPM · hudsongouge
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
VY
VyvoTTS LFM2 350M Jenny
Vyvotts · mradermacher
Params383M
Context125K
Q4_K_M0.3 GB
Tool use
GE
dlp_intents
Gemma · deftgeno
Params268M
Context32K
Smallest0.3 GB
GGUF
QW
swift 1.5 qwen3.8 27b with unsloth iq3 xxs
Qwen · kunthawat
Params461M
Context256K
Smallest10.9 GB
Vision
NO
NORA
Nora · mradermacher
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
FI
v6 Finch 3B HF
Finch · mradermacher
Params3.1B
Context1024K
Q4_K_M1.9 GB
GGUF
QW
Qwen2.5 3B BrutalCritique KoEn
Qwen · hwihwalab
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingReasoningRoleplay

Other sizes

Keep browsing