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
GE
Amoral Gemma3 1B v2
Gemma · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
SA
Sailor-1.8B
Sailor · mradermacher
Params1.84B
Context8K
Q4_K_M1.2 GB
GGUF
RW
RWKV6 3B Chn UnlimitedRP mini chat
Rwkv · btaskel
Params3.1B
Context1024K
Smallest1.9 GB
GGUF
DI
distilgpt2
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
QW
Qwen Qwen3 1.7B
Qwen · tensorblock
Params2.03B
Context40K
Smallest0.9 GB
ReasoningTool use
QW
Ministral 3 3B Qwen3.8 Max Reasoning Distilled
Qwen · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
ReasoningTool useVision
NO
Nous-Capybara-3B-V1.9
Nous · duyntnet
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
QW
Qwen3 VL Embedding 2B
Qwen · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
EmbeddingTool useVision
PO
Pocket Layout Planner 0.8B
Pocket · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool use
MA
MAI UI 2B
Mai · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
Tool useVision
QW
Qwen2.5 3B Instruct Uncensored
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
GE
Gemma 2 2B ArliAI RPMax v1.1
Gemma · mradermacher
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
LL
GPT 5 Distill Llama3.2 3B Instruct Heretic
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
IB
IBM GPT 5.4 Coder 1B
Ibm · mradermacher
Params1.63B
Context128K
Q4_K_M1.0 GB
CodingReasoningTool use
OP
OpenJev 1.7B
Openjev · mradermacher
Params1.72B
Context32K
Q4_K_M1.1 GB
ReasoningTool use
MO
Moss image nsfw uncensored lora
Moss · akhilkumar9439
Params37M
Context—
Smallest0.1 GB
GGUF
TH
The_Elder
The · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
GE
gemma-2b-it
Gemma · mlabonne
Params2.51B
Context8K
Q4_K_M1.5 GB
GGUF
HE
HERETICSEEK 1.5B R1
Hereticseek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
QW
Qwen3.5-0.8B
Qwen · Genrius-AI
Params414M
Context256K
Smallest0.3 GB
ReasoningTool use
LL
Llama 3.2 1b Creative Writing Ablated
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
QW
Qwen2.5 3B Instruct
Qwen · tensorblock
Params3.09B
Context32K
Smallest1.3 GB
GGUF
LL
uukuguy speechless codellama orca platypus 13b 0.10e
Llama · RichardErkhov
Params430M
Context—
Q4_K_M0.0 GB
Coding
QW
Qwen3.8 27B DFlash2
Qwen · Lucebox
Params1.92B
Context256K
Smallest2.0 GB
GGUF
HO
K2 Horizon 0.9B meeting agent zh
Horizon · Luigi
Params1.09B
Context128K
Smallest0.6 GB
GGUF
CL
Cleanup 1
Cleanup · spokenly
Params596M
Context32K
Smallest0.6 GB
GGUF
LU
Lumina-Next-135M
Lumina · jacopof
Params122M
Context8K
Smallest0.5 GB
GGUF
SE
SeaLLMs-v3-1.5B-Chat
Seallms · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
GGUF
LL
Llama 3.2 1B
Llama · tensorblock
Params1.24B
Context128K
Smallest0.6 GB
GGUF
GE
unsloth gemma ft gguf q4 k m
Gemma · Seedawy
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF

Other sizes

Keep browsing