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
ZE
Zephyr 7b Beta Abliterated
Zephyr · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GGUF
QW
Qwen35B Agent R2 Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
KL
Klyrune 2B General
Klyrune · mradermacher
Params2.52B
Context128K
Best fitQ6_K 2.9 GB
ReasoningTool use
RO
RolmOCR
Rolmocr · mradermacher
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
Tool useVision
BO
Borealis Open 1b
Borealis · mradermacher
Params1B
Context32K
Best fitQ6_K 1.7 GB
GGUF
LL
alfredplpl Llama 3 8B Instruct Ja
Llama · mmnga
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
QW
VellumMini 0.1 Qwen3 14B
Qwen · bartowski
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
QW
ThinkingCap Qwen3.6 27B Heretic
Qwen · egibson
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningVision
QW
Qwen3.5 122B A10B Abliterated
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
GGUF
LF
Kulyk En Uk
Lfm · Yehor
Params354M
Context125K
Best fitQ8_0 1.4 GB
GGUF
GE
TheDrummer Gemmasutra Small 4B v1
Gemma · bartowski
Params3.86B
Context8K
Best fitQ3_K_M 4.0 GB
GGUF
CO
Yi Coder 9B
Coder · mradermacher
Params8.83B
Context128K
Best fitIQ2_XS 4.0 GB
Coding
NE
Orchestrator 8B
Nemotron · bartowski
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
GE
Gemma 3 1b It
Gemma · gguf-org
Params1B
Context32K
Best fitBF16 2.7 GB
GGUF
MO
MOSS Image Text Encoder Heretic
Moss · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
CodingReasoningTool use
GE
Gemma 3 12b It Vl HighIQ Polaris Heretic Uncensored Thinking
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
DE
deepseek-coder-1.3B-kexer
DeepSeek · lmstudio-community
Params1.35B
Context16K
Best fitQ8_0 3.5 GB
Coding
KA
Kairos
Kairos · mradermacher
Params8.2B
Context32K
Best fitIQ1_M 4.0 GB
GGUF
CO
COBOL Coder 7B Instruct i1
Cobol · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
Coding
LL
Llama3.1 Nemo Thinker
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
Reasoning
OP
Openhands Lm 1.5b v0.1
Openhands · bartowski
Params1.54B
Context32K
Best fitBF16 3.8 GB
GGUF
GR
Grug 35B A3B
Grug · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
CodingReasoning
ST
Starcoder2 3b
StarCoder · mradermacher
Params3.03B
Context16K
Best fitQ8_0 4.0 GB
Coding
FU
Functiongemma 270m It
Functiongemma · bartowski
Params268M
Context32K
Best fitBF16 1.2 GB
GGUF
BO
Borealis Open 4b
Borealis · mradermacher
Params3.88B
Context128K
Best fitIQ4_NL 4.0 GB
GGUF
QW
Qwen2.5 0.5B Instruct
Qwen · mradermacher
Params494M
Context32K
Best fitQ6_K 1.1 GB
GGUF
VE
Veloxy SLM 3B
Veloxy · mradermacher
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
Tool use
MI
MiMo Ornith 9B AGSI Abliterated HQ
Mimo · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
BE
Behemoth T1 123B
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
ReasoningRoleplay
QW
Qwen2.5 3B Instruct heretic
Qwen · saidutta69
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
GGUF

Other memory sizes

Keep browsing