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
RE
reader lm 1.5b
Reader · QuantFactory
Params1.78B
Context250K
Q4_K_M1.1 GB
GGUF
EU
EuroLLM 1.7B Instruct heretic
Eurollm · saidutta69
Params1.66B
Context4K
Smallest3.3 GB
GGUF
LL
Llama 3.2 3B Instruct heretic ablitered uncensored
Llama · tinyopsec
Params3.2B
Context128K
Q4_K_M2.0 GB
GGUF
ME
melotts en v3
Melotts · cstr
Params95M
Context—
Smallest0.1 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B Abliterated
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
DE
tiny random deepseek distill qwen
DeepSeek · sammysun0711
Params514M
Context128K
Smallest0.6 GB
GGUF
TI
Tinystories Lay8 Hs512 Hd8 33M
Tinystories · RichardErkhov
Params165M
Context512
Q4_K_M0.1 GB
GGUF
IN
Internlm2_5 1_8b Chat
InternLM · legraphista
Params1.89B
Context32K
Smallest0.5 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · second-state
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
TI
minecraft
Tinyllama · QuantFactory
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
PO
Pony Realism
Pony · nuupy
Params2.57B
Context—
Q4_K_M1.6 GB
GGUF
QW
BooruNL
Qwen · cooperdk
Params752M
Context256K
Q4_K_M0.5 GB
GGUF
SK
SkinTokens GGUF BF16
Skintokens · chibifire
Params29M
Context—
Smallest0.1 GB
GGUF
QW
archai jev qwen 1.5b
Qwen · nickprock
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
GR
Gradience T1 3B Preview
Gradience · bartowski
Params3.09B
Context32K
Q4_K_M1.9 GB
Reasoning
QW
Stewmind 1.7b
Qwen · Erog0291
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
SM
SmolLM2 135M Instruct
SmolLM · mradermacher
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
CS
CSM 1B
Csm · BricksDisplay
Params457M
Context—
Q4_K_M0.8 GB
GGUF
QW
Replete-Coder-Qwen2-1.5b
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingTool use
QW
MegaScience Qwen
Qwen · prithivMLmods
Params1.54B
Context128K
Q4_K_M1.0 GB
GGUF
LL
Llama 3.2 SUN 2.5B Chat
Llama · mradermacher
Params2.47B
Context128K
Q4_K_M1.5 GB
ReasoningTool use
EV
EventTwin
Eventtwin · mradermacher
Params568M
Context8K
Q4_K_M0.4 GB
CodingEmbedding
HO
HOT Step CPP SuperSep
Hot · scragnog
Params67M
Context—
Smallest0.3 GB
GGUF
JN
xd v2
Jnjj · jnjj
Params13M
Context2K
Q4_K_M0.0 GB
GGUF
AR
arco 75k
Arco · mradermacher
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
JI
jina embeddings v5 omni nano clustering
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
EmbeddingReasoningTool use
OP
OpenELM 1_1B
Openelm · mradermacher
Params1.08B
Context2K
Q4_K_M0.7 GB
GGUF
CS
CSCupcakeCoder
Cscupcakecoder · mradermacher
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
GR
granite speech 4.1 2b plus
Granite · cstr
Params2.32B
Context—
Smallest1.7 GB
GGUF
HE
HelpingAI 3B hindi
Helpingai · QuantFactory
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF

Other sizes

Keep browsing