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
MI
MiniCPM V 4.7 35B A3B
MiniCPM · openbmb
Params34.7B
Context256K
Best fitF16 2.0 GB
ReasoningTool useVision
GR
Granite 4.2 3b
Granite · ibm-granite
Params3.66B
Context128K
Best fitQ5_1 3.9 GB
GGUF
LF
LFM2.5 Audio 1.5B
Lfm · LiquidAI
Params190M
Context125K
Best fitF16 3.0 GB
Vision
QW
Qwen3.5-0.8B
Qwen · unsloth
Params752M
Context256K
Best fitBF16 2.4 GB
Vision
QW
Ternary-Bonsai-2-2B
Qwen · prism-ml
Params1.88B
Context256K
Smallest0.4 GB
Vision
GP
gpt-oss-20b
gpt-oss · ggml-org
Params870M
Context128K
Best fitBF16 2.2 GB
GGUF
GE
Gemma 3 1b It
Gemma · ggml-org
Params1B
Context32K
Best fitF16 2.7 GB
GGUF
SM
TwIL LM3
SmolLM · webAI-Official
Params3.08B
Context64K
Best fitQ6_K 3.6 GB
Reasoning
QW
Qwen2.5-Vl-7B-Instruct
Qwen · unsloth
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
Vision
GP
gpt-oss-120b
gpt-oss · ggml-org
Params800M
Context128K
Best fitBF16 2.1 GB
GGUF
QW
qwen2.5-3b-instruct
Qwen · Qwen
Params3.4B
Context32K
Best fitQ6_K 3.6 GB
GGUF
QW
Qwen2.5 Coder 1.5B Instruct GGUF
Qwen · Qwen
Params1.78B
Context32K
Best fitQ8_0 2.6 GB
Coding
QW
Qwen2.5 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
GGUF
MI
s1 mini
Mini · superwhisper
Params752M
Context40K
Best fitF16 2.9 GB
GGUF
SP
Spark X2.5 1.7B
Spark · XHToken
Params1.71B
Context1024K
Best fitQ8_0 2.8 GB
GGUF
QW
Qwen3-1.7B
Qwen · unsloth
Params1.72B
Context40K
Best fitQ8_K_XL 3.8 GB
GGUF
QW
Qwen3 0.6B Instruct
Qwen · Qwen
Params596M
Context40K
Best fitQ8_0 2.1 GB
GGUF
GE
gemma 4 12B it qat
Gemma · unsloth
Params440M
Context256K
Best fitBF16 2.4 GB
Vision
MI
MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking
MiniCPM · GnLOLot
Params1.08B
Context128K
Best fitF16 2.9 GB
ReasoningTool use
BG
bge small en v1.5
BGE · unsloth
Params33M
Context512
Best fitF16 0.7 GB
Embedding
MU
Muse Glimmer 30B
Muse · meta-models
Params27.9B
Context128K
Best fitQ4_K_M 2.3 GB
Vision
QW
Qwen3-Vl-8B-Instruct
Qwen · unsloth
Params8.19B
Context256K
Best fitIQ1_S 4.0 GB
Vision
MX
mxbai-embed-large-v1
Mxbai · ChristianAzinn
Params334M
Context512
Q4_K_M0.2 GB
Embedding
CA
Carbon 3B
Carbon · HuggingFaceBio
Params3.45B
Context32K
Best fitQ6_K 3.8 GB
GGUF
MI
MiniCPM5 1B Claude Opus Fable5 Thinking
MiniCPM · GnLOLot
Params1.08B
Context128K
Best fitF16 2.9 GB
Reasoning
EX
Experiment26 7B passthrough 10slice
Experiment · babybirdprd
Params7B
Context—
Best fitQ4_K_M 0.5 GB
GGUF
QW
Qwen3.5 9B
Qwen · bartowski
Params9.2B
Context256K
Q4_K_M6.2 GB
Vision
LF
LFM2.5 24B A2B Uncensored
Lfm · AtomicChat
Params24B
Context128K
Q4_K_M15.4 GB
ReasoningTool use
QW
Qwen3Vl 2b Instruct
Qwen · Qwen
Params1.72B
Context256K
Best fitQ8_0 3.3 GB
Vision
QW
Qwen3.8 27B Uncensored
Qwen · azukivc
Params27.3B
Context256K
Best fitF16 3.6 GB
GGUF

Other memory sizes

Keep browsing