GGUF models that fit in 48 GB
201364 GGUF language models have at least one quant whose estimated memory use is 48 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.
MI
mistralai_mistral-7b-instruct-v0.2
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
LL
Models Meta Llama Llama 3.2 1B Instruct
Llama · MaziyarPanahi
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ8_0 33.8 GB
FR
FrogNano 4B 2609
Frognano · bartowski
Params4.33B
Context256K
Best fitBF16 10.3 GB
SQ
sqlcoder 7b 2
Sqlcoder · MaziyarPanahi
Params6.74B
Context16K
Q4_K_M4.1 GB
QW
Models Qwen Qwen3 4B Instruct 2507
Qwen · MaziyarPanahi
Params4B
Context256K
Q4_K_M2.5 GB
QW
Qwen2.5 VL 7B Instruct
Qwen · lmstudio-community
Params7.62B
Context125K
Best fitQ8_0 9.1 GB
NA
Nanbeige4.3-33B
Nanbeige · AtomicChat
Params33.1B
Context512K
Best fitQ8_0 37.4 GB
NE
NVIDIA Nemotron 3 Nano 4B
Nemotron · lmstudio-community
Params3.97B
Context1024K
Best fitQ8_0 11.8 GB
QW
Qwen Image 2.1 Turbo Uncensored
Qwen · TechnoBaptist
Params8.2B
Context256K
Best fitBF16 18.1 GB
QW
Qwen Image 2.1 PE I2I Heretic
Qwen · pottokao
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
LL
Llama 3.2 3B Instruct
Llama · bartowski
Params3.61B
Context128K
Best fitF16 8.7 GB
DG
dgpl experimental 1
Dgpl · dgpl
Params550M
Context—
Best fitF16 1.8 GB
QW
Qwen_Qwen3.5 2B
Qwen · lmstudio-community
Params1.88B
Context256K
Best fitQ8_0 2.9 GB
LI
H2O Lightning 4B
Lightning · h2oai
Params4.21B
Context256K
Best fitBF16 10.0 GB
LL
Models Meta Llama Llama 3.2 3B Instruct
Llama · MaziyarPanahi
Params3.21B
Context128K
Q4_K_M2.0 GB
FL
Flint INT4 Preview
Flint · RecursiveSI
Params39.8B
Context256K
Best fitQ4_1 27.3 GB
OR
Ornith 1.5 35B A3B UNCENSORED
Ornith · dealignai
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
JA
JackOD 9B Coder
Jackod · ManniX-ITA
Params9.2B
Context256K
Best fitF16 20.0 GB
PH
Phi 4 Mini Instruct
Phi · MaziyarPanahi
Params3.84B
Context128K
Q4_K_M2.5 GB
TE
Hy MT2 30B A3B
Tencent · tencent
Params30B
Context256K
Best fitQ8_0 33.3 GB
LL
Dolphin 3.0 Llama 3.1 8B
Llama · dphn
Params8B
Context128K
Best fitF16 17.6 GB
NE
Nvidia-Nemotron-3.5-Lightning-30B-A3B
Nemotron · unsloth
Params32.9B
Context1024K
Best fitQ8_K_XL 46.2 GB
QW
Qwen3 Embedding 8B
Qwen · Qwen
Params7.57B
Context40K
Best fitF16 16.8 GB
GE
Winnow E4B
Gemma · EldanRing
Params78M
Context128K
Best fitBF16 15.7 GB
LL
chronicle narrator
Llama · GWsuryaYT
Params8B
Context128K
Best fitQ4_K_M 6.5 GB
GL
GLM OCR
GLM · ggml-org
Params891M
Context128K
Best fitF16 2.9 GB
QW
Qwen3-30B-A3B
Qwen · unsloth
Params30.5B
Context40K
Best fitQ8_K_XL 37.3 GB
QW
Models Qwen Qwen2.5 7B Instruct
Qwen · MaziyarPanahi
Params7.62B
Context32K
Q4_K_M4.7 GB
LL
Llama-3.2-1B-Instruct
Llama · unsloth
Params1.24B
Context128K
Best fitF16 3.2 GB