GGUF models that fit in 24 GB

193369 GGUF language models have at least one quant whose estimated memory use is 24 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 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.5 9B DeepSeek V4 Flash
Qwen · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
ReasoningVision
MI
MiniCPM5 1B
MiniCPM · openbmb
Params1.08B
Context128K
Best fitF16 2.9 GB
Tool use
QW
Qwen2.5 VL 7B Instruct
Qwen · mradermacher
Params7.62B
Context125K
Best fitF16 16.2 GB
Vision
GR
ibm granite granite 20b code base
Granite · RichardErkhov
Params1.9B
Context—
Best fitQ3_K_S 10.5 GB
Coding
LL
CreativeWriter Llama3.2 3B
Llama · theprint
Params3.21B
Context128K
Best fitF16 7.9 GB
GGUF
QW
Qwen3.8 27B Uncensored OrcaRouter
Qwen · chimingw
Params27.3B
Context256K
Best fitQ5_K_M 22.2 GB
Tool useVision
LL
models--MaziyarPanahi--Llama-3-8B-Instruct-32k-v0.1
Llama · MaziyarPanahi
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma 4 E4B It
Gemma · bartowski
Params7.5B
Context128K
Best fitBF16 17.0 GB
Vision
LL
Dorna2 Llama3.1 8B Instruct
Llama · aeranginkaman
Params8B
Context128K
Best fitQ4_K_M 6.5 GB
GGUF
MI
Mistral Small 3.2 24B Instruct 2506
Mistral · bartowski
Params23.6B
Context128K
Best fitQ6_K_L 21.5 GB
Vision
GE
Huihui gemma 4 12B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params11.9B
Context256K
Best fitQ4_0 9.0 GB
Vision
MI
mistralai_mistral-7b-instruct-v0.2
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
LL
Models Meta Llama Llama 3.2 1B Instruct
Llama · MaziyarPanahi
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ5_K_M 23.0 GB
Coding
FR
FrogNano 4B 2609
Frognano · bartowski
Params4.33B
Context256K
Best fitBF16 10.3 GB
Vision
SQ
sqlcoder 7b 2
Sqlcoder · MaziyarPanahi
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Models Qwen Qwen3 4B Instruct 2507
Qwen · MaziyarPanahi
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
QW
Qwen2.5 VL 7B Instruct
Qwen · lmstudio-community
Params7.62B
Context125K
Best fitQ8_0 9.1 GB
Vision
NA
Nanbeige4.3-33B
Nanbeige · AtomicChat
Params33.1B
Context512K
Best fitQ4_K_M 23.4 GB
ReasoningTool use
NE
NVIDIA Nemotron 3 Nano 4B
Nemotron · lmstudio-community
Params3.97B
Context1024K
Best fitQ8_0 11.8 GB
GGUF
QW
Qwen Image 2.1 Turbo Uncensored
Qwen · TechnoBaptist
Params8.2B
Context256K
Best fitBF16 18.1 GB
CodingVision
QW
Qwen Image 2.1 PE I2I Heretic
Qwen · pottokao
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
Vision
LL
Llama 3.2 3B Instruct
Llama · bartowski
Params3.61B
Context128K
Best fitF16 8.7 GB
GGUF
DG
dgpl experimental 1
Dgpl · dgpl
Params550M
Context—
Best fitF16 1.8 GB
Reasoning
QW
Qwen_Qwen3.5 2B
Qwen · lmstudio-community
Params1.88B
Context256K
Best fitQ8_0 2.9 GB
Vision
LI
H2O Lightning 4B
Lightning · h2oai
Params4.21B
Context256K
Best fitBF16 10.0 GB
ReasoningTool useVision
LL
Models Meta Llama Llama 3.2 3B Instruct
Llama · MaziyarPanahi
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
OR
Ornith 1.5 35B A3B UNCENSORED
Ornith · dealignai
Params35.5B
Context256K
Best fitQ4_K_M 22.9 GB
ReasoningVision
JA
JackOD 9B Coder
Jackod · ManniX-ITA
Params9.2B
Context256K
Best fitF16 20.0 GB
CodingReasoningTool use
PH
Phi 4 Mini Instruct
Phi · MaziyarPanahi
Params3.84B
Context128K
Q4_K_M2.5 GB
GGUF

Other memory sizes

Keep browsing