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
QW
EUAIAct Qwen2.5 0.5B Edge
Qwen · sallani
Params494M
Context32K
Best fitQ4_K_M 1.0 GB
GGUF
IN
InternVL3 1B Instruct
Internvl · ggml-org
Params630M
Context32K
Best fitF16 1.9 GB
Vision
QW
Qwen2.5 1.5B Instruct
Qwen · lmstudio-community
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
GGUF
JA
Jan nano
Jan · Menlo
Params4B
Context40K
Best fitIQ4_XS 4.0 GB
GGUF
XY
Xyntetik Kvist 14B
Xyntetik · mradermacher
Params14.4B
Context128K
Q4_K_M10.3 GB
Tool use
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Best fitQ2_K 3.9 GB
GGUF
HU
Hunyuan 0.5B Instruct
Hunyuan · bartowski
Params539M
Context256K
Best fitBF16 2.4 GB
GGUF
GR
Granite 3.1 2b Instruct
Granite · bartowski
Params2.53B
Context128K
Best fitQ8_0 3.9 GB
GGUF
QW
Qwen3-4B-abliterated
Qwen · Mungert
Params4B
Context40K
Best fitQ4_0 4.0 GB
GGUF
PY
Pythia 410m
Pythia · mradermacher
Params405M
Context2K
Best fitQ4_0 1.6 GB
GGUF
GE
Vikhr-Gemma-2B-instruct
Gemma · Vikhrmodels
Params2.61B
Context8K
Best fitQ6_K 3.5 GB
GGUF
FI
SUFE AIFLM Lab Fin R1
Fin · bartowski
Params7.6B
Context32K
Best fitQ2_K 4.0 GB
Reasoning
QW
Qwen3 Uncensored TextEncoders Klein Z Image Anima
Qwen · LuffyTheFox
Params596M
Context40K
Best fitF16 2.6 GB
Coding
TE
Terminal RSI 27B
Terminal · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
CodingReasoningTool use
LI
LightOnOCR 3 0.8B
Lightonocr · NANI-Nithin
Params752M
Context256K
Best fitBF16 2.4 GB
GGUF
PH
phi-4-mini-instruct
Phi · Mungert
Params3.84B
Context128K
Best fitQ4_0 4.0 GB
CodingReasoning
HO
Holo 3.1 4B
Holo · prithivMLmods
Params4.84B
Context256K
Best fitQ3_K_S 3.9 GB
Vision
SE
SexyGPT v3 Thinking Female
Sexygpt · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplay
OU
OuteTTS 0.2 500M
Outetts · OuteAI
Params500M
Context32K
Q4_K_M0.4 GB
GGUF
SE
SenseNova U1 8B MoT SFT
Sensenova · mradermacher
Params9.35B
Context256K
Q4_K_M5.7 GB
CodingReasoningTool use
GR
Kiesel v2
Granite · mradermacher
Params8.8B
Context128K
Best fitIQ1_S 4.0 GB
ReasoningTool use
LL
Akikawa 3.3 1b Roleplay 128K
Llama · Green-Eye
Params1.24B
Context128K
Best fitF16 3.2 GB
Roleplay
HO
K2 Horizon 3.7B
Horizon · NANI-Nithin
Params5.06B
Context512K
Best fitQ2_K 3.9 GB
GGUF
QW
Qwen3.5 4B
Qwen · gguf
Params4.33B
Context256K
Best fitQ3_K_M 3.9 GB
Vision
GR
Granite 4.0 H 1b
Granite · ibm-granite
Params1.46B
Context1024K
Best fitQ6_K 3.7 GB
GGUF
TE
NaviDC OCR
Teleocr · nandraj
Params752M
Context125K
Best fitF16 2.9 GB
Vision
GE
Huihui Gemma 3n E4B It Abliterated
Gemma · bartowski
Params6.9B
Context32K
Best fitQ2_K 3.8 GB
GGUF
MO
MolOptAgent 7B
Moloptagent · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
GGUF
XL
xLAM 2 3b Fc R
Xlam · Salesforce
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
Tool use
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · unsloth
Params1.54B
Context128K
Best fitF16 3.8 GB
Coding

Other memory sizes

Keep browsing