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
PI
piper en US lessac medium
Piper · cstr
Params16M
Context—
Smallest0.0 GB
GGUF
QW
Coder GRPO 3B
Qwen · yasserrmd
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
LL
Llama 3.1 8B Pingala8 2bit
Llama · Genrius-AI
Params2.89B
Context128K
Smallest2.4 GB
GGUF
TU
turkish pii detection
Turkish · halilneed
Params268M
Context32K
Smallest0.3 GB
GGUF
QW
Qwen2.5 Coder 1.5B Instruct Abliterated
Qwen · RichardErkhov
Params1.78B
Context32K
Q4_K_M1.1 GB
Coding
CO
codegemma-2b
Codegemma · lmstudio-community
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Qwen2.5 Coder 3B Instruct
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
DU
DualMind
Dualmind · reaperdoesntknow
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
QW
Qwen2.5 Coder 3B Instruct
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
SQ
squad-0.8b documents expert (LoRA r64: lora_A Q2_K = its 2-bit rows, lora_B Q8_0)
Squad · labqoat
Params11M
Context—
Smallest0.0 GB
GGUF
QW
Qwen2.5 1.5B Instruct abliterated
Qwen · SonGT1
Params1.54B
Context32K
Smallest1.6 GB
Tool use
DA
danube2-1.8b-Synthia-v1.3
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
LL
LLaMA3 Reasoning
Llama · mradermacher
Params157M
Context128
Q4_K_M0.1 GB
Reasoning
NE
OpenReasoning Nemotron 1.5B
Nemotron · bartowski
Params1.54B
Context128K
Q4_K_M1.0 GB
Reasoning
QW
Replete Coder Qwen2 1.5b
Qwen · bartowski
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingTool use
LL
Llama 3.2 1B Instruct Uncensored
Llama · brittlewis12
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB LiLiCorr
Nemotron · magnitudedev
Params1.11B
Context256K
Smallest1.0 GB
ReasoningTool use
QW
Qwen3 TTS 12Hz 1.7B CustomVoice
Qwen · BricksDisplay
Params694M
Context32K
Q4_K_M1.1 GB
GGUF
MI
Lite-Mistral-150M-v2-Instruct
Mistral · mradermacher
Params157M
Context2K
Q4_K_M0.1 GB
GGUF
AN
Anything
Anything · mzwing
Params1.07B
Context—
Smallest1.3 GB
GGUF
QW
rStar Coder Qwen3 0.6B
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
CodingReasoningTool use
QW
Qwen2 Math 1.5B Instruct
Qwen · mradermacher
Params1.54B
Context4K
Q4_K_M1.0 GB
GGUF
LF
LFM2.5 VL 3B Heretic
Lfm · AX1Y2JP
Params2.7B
Context125K
Q4_K_M1.7 GB
Vision
SE
SEX_ROLEPLAY.v4 3.2 1B
Sex · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
RoleplayTool use
HU
Huihui LFM2.5 1.2B Instruct Abliterated
Huihui · mradermacher
Params1.17B
Context125K
Q4_K_M0.7 GB
Tool use
QW
Qwen3 Shining Lucy CODER 3.5B Brainstorm20x E32
Qwen · mradermacher
Params3.38B
Context40K
Q4_K_M2.1 GB
CodingReasoningTool use
QW
kAI Bolt 0.8B
Qwen · Franci11
Params780M
Context256K
Q4_K_M0.6 GB
Vision
LL
ReWiz Llama 3.2 3B
Llama · theprint
Params3.21B
Context128K
Q4_K_M2.0 GB
ReasoningTool use
QW
Qwen3 TTS
Qwen · Solidaxel
Params142M
Context32K
Smallest0.2 GB
GGUF
QW
Qwen3-TTS-Tokenizer-12Hz
Qwen · CC-TM
Params915M
Context—
Q4_K_M0.3 GB
GGUF

Other sizes

Keep browsing