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
LL
Reasoning Llama 1b v0.1
Llama · bartowski
Params1.24B
Context128K
Q4_K_M0.8 GB
Reasoning
QW
Qwopus3.8 27B Flash
Qwen · Jackrong
Params461M
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
CR
CREPE (tiny)
Crepe · cstr
Params22M
Context—
Smallest0.0 GB
GGUF
QW
Qwen3 1.7B Coder Distilled SFT
Qwen · reaperdoesntknow
Params2.03B
Context40K
Q4_K_M1.3 GB
CodingReasoningTool use
ST
stable code instruct 3b
Stable · QuantFactory
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
LL
Llama 3.2 uncensored erotica
Llama · hungng
Params3.21B
Context128K
Smallest6.4 GB
GGUF
SM
Biggie SmoLlm 0.15B Base
SmolLM · mradermacher
Params181M
Context2K
Q4_K_M0.1 GB
GGUF
LF
LFM2.5 1.2B Nova Function Calling
Lfm · NovachronoAI
Params1.17B
Context125K
Q4_K_M0.7 GB
Tool use
RU
RusMind Malysh 4.7
Rusmind · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool use
GR
Granite 3.1 3b A800M Instruct
Granite · bartowski
Params3.3B
Context128K
Q4_K_M2.0 GB
GGUF
QW
Qwen2.5 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
CU
CursorCore QW2.5 1.5B i1
Cursorcore · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
QW
Qwen_Qwen3 VL 2B Instruct
Qwen · lmstudio-community
Params1.72B
Context256K
Q4_K_M1.1 GB
Vision
QW
Bella Bartender Qwen3 1.7b
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
GW
Vt Gwen 2.5 3b Q4_k_m Gguf
Gwen · vinhnx90
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
SP
Spark X2.6 1.7B
Spark · mradermacher
Params1.71B
Context1024K
Q4_K_M1.1 GB
ReasoningTool use
LL
Llama 3.2 1B NSFW Open Erotic
Llama · Novaciano
Params1.5B
Context128K
Smallest1.0 GB
Tool use
NO
Nova-1.1-0.8B
Nova · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
Tool use
GP
gpt2
Gpt · QuantFactory
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
QW
Qwen2 1.5B Instruct
Qwen · Goekdeniz-Guelmez
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
QW
Qwen3 0.6B Abliterated
Qwen · bartowski
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
MO
MotionBricks G1 GGML
Motionbricks · LocalAI-io
Params137M
Context—
Smallest0.0 GB
GGUF
CO
cohere transcribe arabic 07 2026
Cohere · cstr
Params2.07B
Context—
Smallest0.0 GB
GGUF
RH
rho-math-1b-interpreter-v0.1
Rho · RichardErkhov
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
QW
Qwen2.5 1.5B Instruct
Qwen · QuantFactory
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Qwen3.6 35B A3B DFlash2
Qwen · aminya
Params526M
Context256K
Q4_K_M0.3 GB
GGUF
CA
canary 1b v2
Canary · cstr
Params980M
Context—
Smallest0.0 GB
GGUF
MI
Ministral 3b instruct
Mistral · mradermacher
Params3.32B
Context128K
Q4_K_M2.0 GB
GGUF
PY
Pythia 1.4b
Pythia · mradermacher
Params1.41B
Context2K
Q4_K_M0.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B Heretic
DeepSeek · saidutta69
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use

Other sizes

Keep browsing