GGUF models that fit in 4 GB

79024 GGUF language models have at least one quant whose estimated memory use is 4 GB or less at 8K context. Each card shows the largest quant that fits. Sizes run from 1M to 20260731B parameters. The longest trained context is 1280000K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
ADG CoT LLaMa3 8B
Llama · mradermacher
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
NO
North Mini Code 1.0
North · mradermacher
Params30.5B
Context488K
Q4_K_M18.6 GB
CodingReasoningTool use
MU
G4 E4B Musica v1
Musica · bartowski
Params7.5B
Context128K
Q4_K_M5.4 GB
ReasoningRoleplayVision
NE
Neuron 46x4B
Neuron · mradermacher
Params125B
Context256K
Q4_K_M75.8 GB
Tool use
JA
JarvisArt 1208
Jarvisart · mradermacher
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
Vision
LI
Lite Oute 1 300M Instruct
Lite · mradermacher
Params300M
Context4K
Best fitF16 1.4 GB
GGUF
LA
labse
Labse · ChristianAzinn
Params470M
Context512
Q4_K_M0.4 GB
Embedding
NI
Nightshade-Violet-12B
Nightshade · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
QW
Qwen2.5 1.5B Instruct heretic
Qwen · saidutta69
Params1.54B
Context32K
Best fitF16 3.8 GB
GGUF
MU
multilingual e5 small
Multilingual · TwinSunsLLC
Params118M
Context511
Best fitQ8_0 0.8 GB
Embedding
NA
Nanonets OCR2 3B
Nanonets · mradermacher
Params3.09B
Context125K
Best fitQ6_K 3.3 GB
Vision
QW
Qwen3.5 4B
Qwen · prithivMLmods
Params4.33B
Context256K
Best fitQ3_K_M 3.9 GB
Vision
LL
Meta Llama Llama 3.2 3B Instruct Heretic Nosyco
Llama · mradermacher
Params3.21B
Context128K
Best fitQ5_K_M 3.8 GB
Tool use
IN
Index Nailong 2B
Index · IndexTeam
Params1.88B
Context256K
Best fitQ8_0 2.9 GB
Vision
CS
Csg Wukong 1B
Csg · mradermacher
Params1.1B
Context2K
Best fitQ6_K 1.6 GB
Coding
GE
Gemma4 12B Uncensored HauhauCS 1M
Gemma · satgeze
Params11.9B
Context256K
Smallest0.3 GB
Vision
MI
MiniCPM O 2_6
MiniCPM · bartowski
Params7.6B
Context32K
Best fitQ2_K 4.0 GB
CodingVision
QW
Qwen3 53B A3B 2507 THINKING TOTAL RECALL v2 MASTER CODER
Qwen · mradermacher
Params53B
Context256K
Q4_K_M32.1 GB
CodingReasoning
SN
Snowpiercer 15B v3
Snowpiercer · bartowski
Params15B
Context64K
Q4_K_M9.1 GB
GGUF
AN
Andy 4.2
Andy · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Replete LLM V2.5 Qwen 0.5b
Qwen · bartowski
Params630M
Context32K
Best fitF16 1.9 GB
GGUF
LL
Llama-3-8B-Magpie-Mix-SFT-v0.1
Llama · mradermacher
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
WH
whisper base
Whisper · oxide-lab
Params73M
Context—
Best fitQ4_0 0.6 GB
GGUF
DO
Dolphin v2 8b Abliterated
Dolphin · mradermacher
Params8.19B
Context40K
Best fitIQ1_M 4.0 GB
GGUF
SE
Selene 3B Instruct
Selene · mradermacher
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
GGUF
LL
Dolphin 3.0 Llama 3.2 3B
Llama · mradermacher
Params3.21B
Context128K
Best fitQ5_K_M 3.8 GB
CodingTool use
LL
Llama 3.2 Taiwan 3B Instruct
Llama · lianghsun
Params3.61B
Context128K
Best fitQ5_0 4.0 GB
GGUF
RE
Reggie v3 7b
Reggie · mradermacher
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
ReasoningVision
HU
Huihui Qwopus3.5 9B v3 Abliterated
Huihui · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Reasoning
DR
DrakIdol Roleplayer 1.0
Drakidol · Emerald7664
Params3.88B
Context128K
Best fitIQ4_NL 4.0 GB
Roleplay

Other memory sizes

Keep browsing