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
QW
Huihui Qwen3.5 2B Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
LL
llama 161M 100B
Llama · QuantFactory
Params162M
Context1K
Q4_K_M0.1 GB
GGUF
HA
hassaku-xl-illustrious.fp16.gguf
Hassaku · void-gryph
Params2.57B
Context77
Q4_K_M1.4 GB
GGUF
SN
snack models
Snack · TurtletortOS
Params1.73B
Context125K
Smallest1.0 GB
ReasoningTool useVision
QW
qwen3 0.6b text embedding
Qwen · akahana
Params596M
Context32K
Smallest0.6 GB
EmbeddingReasoningTool use
SM
SmolLM2 360M Instruct Heretic
SmolLM · mradermacher
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · ThomasBaruzier
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
BO
Boris 1.3 125M Instruct
Boris · opencerebral
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
TH
The_Elder v2
The · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
CA
Carrot-Ko-2B-Instruct
Carrot · mradermacher
Params2.34B
Context32K
Q4_K_M1.5 GB
GGUF
GE
Gemma 2 2b
Gemma · mradermacher
Params2.61B
Context8K
Q4_K_M1.7 GB
Tool use
RW
Rwkv7 2.9B G1
Rwkv · Mungert
Params2.95B
Context1024K
Q4_K_M2.0 GB
Reasoning
JA
Javi0.3 2B
Javi · mradermacher
Params1.94B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
QW
Qwen3 0.6B Abliterated
Qwen · mlabonne
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
TI
TinyLlama Friendly Psychotherapist
Tinyllama · mradermacher
Params1.1B
Context32K
Q4_K_M0.7 GB
GGUF
QW
qwen2.5 .5b abliterated i1
Qwen · mradermacher
Params630M
Context32K
Q4_K_M0.5 GB
GGUF
LL
FuseChat Llama 3.2 1B Instruct
Llama · bartowski
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
GE
gemma 2 baku 2b it
Gemma · QuantFactory
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
gemma-2b
Gemma · mlabonne
Params2.51B
Context8K
Q4_K_M1.5 GB
GGUF
MI
MiniCPM V 4.7 1B Pashto Base
MiniCPM · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool useVision
IN
InternVL2_5 1B
Internvl · ggml-org
Params630M
Context32K
Smallest0.7 GB
Tool useVision
LL
MiniCPM-S-1B-sft-llama-format
Llama · mradermacher
Params1.47B
Context4K
Q4_K_M0.9 GB
GGUF
TI
TinyMixtral 4x248M MoE i1
Tinymixtral · mradermacher
Params701M
Context32K
Q4_K_M0.4 GB
GGUF
QW
Qwen3.5 0.8B Coder Calude Full
Qwen · rahul7star
Params752M
Context256K
Q4_K_M0.5 GB
CodingReasoningTool use
RE
Refact 1 6 base
Refact · QuantFactory
Params1.59B
Context4K
Q4_K_M1.0 GB
Coding
PR
PrathameshLLM 2B
Prathameshllm · pmking27
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Qwen2.5 3B Instruct
Qwen · Alexs28
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
SM
SmolLM 1.7B
SmolLM · QuantFactory
Params1.71B
Context2K
Q4_K_M1.1 GB
GGUF
QW
Aether-Qwen2-0.5B-SFT-v0.0.1
Qwen · mradermacher
Params494M
Context128K
Q4_K_M0.4 GB
Coding
GR
Granite Speech 4.1 2b
Granite · ibm-granite
Params1.84B
Context4K
Q4_K_M1.1 GB
Vision

Other sizes

Keep browsing