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
PH
phonon 40m en
Phonon · gradium
Params51M
Context—
Smallest0.1 GB
GGUF
AE
AesCode 8B
Aescode · bartowski
Params8.19B
Context256K
Q4_K_M5.2 GB
CodingVision
IM
imgmodel
Imgmodel · koboldcpp
Params3.47B
Context40K
Best fitQ8_0 3.5 GB
Vision
OV
OvisOCR3
Ovisocr · mradermacher
Params752M
Context256K
Best fitF16 2.4 GB
ReasoningTool useVision
ME
Medgemma 4b It
Medgemma · bartowski
Params3.88B
Context128K
Best fitIQ4_NL 4.0 GB
ReasoningVision
LF
LFM2.5 2.6B Heretic Abliterated
Lfm · Abiray
Params2.7B
Context125K
Best fitQ3_K_M 3.9 GB
GGUF
NE
nexus finance
Nexus · King3Djbl
Params1.54B
Context32K
Best fitF16 3.8 GB
GGUF
LL
FILM6912 Meta Llama 3.1 8B Instruct
Llama · RichardErkhov
Params8B
Context—
Best fitQ3_K_L 3.7 GB
GGUF
LL
Llama Artemis
Llama · mradermacher
Params8.2B
Context128K
Best fitIQ1_M 3.8 GB
GGUF
MI
MiniCPM V 4
MiniCPM · openbmb
Params3.6B
Context32K
Best fitQ6_K 3.7 GB
CodingVision
QW
Qwen3.6 35B A3B MTP APEX I MiniPlus V2.1
Qwen · IsValorum
Params35.5B
Context256K
Best fitQ8_0 3.2 GB
ReasoningTool useVision
HU
HunyuanOCR
Hunyuanocr · ggml-org
Params539M
Context32K
Best fitBF16 2.4 GB
Vision
QW
Qwen3 4B Instruct 2507 Polaris Alpha Distill Heretic Abliterated
Qwen · mradermacher
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
GGUF
IM
Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75
Image · BennyDaBall
Params4B
Context40K
Best fitMXFP4 4.0 GB
Coding
RW
Rwkv 6 World 7b
Rwkv · latestissue
Params7.64B
Context1024K
Best fitQ2_K 3.8 GB
GGUF
HO
K2-Horizon-32B
Horizon · bartowski
Params34.8B
Context512K
Q4_K_M22.0 GB
GGUF
QW
Huihui Qwen3.5 0.8B abliterated claude mythos distilled 25k
Qwen · azminawwar
Params773M
Context256K
Best fitBF16 2.5 GB
ReasoningTool useVision
QW
Qwen3.5 27B Ultra Uncensored Heretic v2
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
PY
Pyrut 8B Instruct Uncensored i1
Pyrex · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
CodingTool use
AP
Apex 35B V1.0
Apex · bartowski
Params35.5B
Context256K
Q4_K_M22.8 GB
ReasoningTool useVision
QW
Qwen2.5 Coder 0.5B Instruct
Qwen · bartowski
Params494M
Context32K
Best fitF16 1.6 GB
Coding
PH
phonon 40m es
Phonon · gradium
Params51M
Context—
Smallest0.1 GB
GGUF
GE
gemma 3 4b it qat q4 0
Gemma · google
Params3.88B
Context—
Best fitQ4_0 4.0 GB
Vision
PH
phonon 40m multilingual
Phonon · gradium
Params51M
Context—
Smallest0.1 GB
GGUF
GE
Gemma 4 E4B Abliterated Uncensored
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
Roleplay
QW
Raw Uncensored Qwen3 14b Heretic Recovered
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
LL
Llama 3.2 1B Instruct Uncensored
Llama · mradermacher
Params1.24B
Context128K
Best fitQ6_K 1.8 GB
GGUF
HY
Hy MT2 7B
mradermacher
Params7.5B
Context256K
Best fitIQ2_XS 4.0 GB
GGUF
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored GGUF UltraOptimised DSpark MTP
Qwen · Solstice-AI
Params26.9B
Context256K
Best fitQ8_0 2.7 GB
ReasoningVision
NE
Nex N2 Mini
Nex · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision

Other memory sizes

Keep browsing