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.
RA
Raon 1 mini preview
Raon · NANI-Nithin
Params28.8B
Context256K
Best fitQ6_K 44.2 GB
LL
Nous Hermes Llama2 70B
Llama · TheBloke
Params69B
Context4K
Best fitQ4_K_M 44.6 GB
QW
Qwen2.5 3B Instruct
Qwen · ThomasBaruzier
Params3.09B
Context32K
Best fitF16 7.0 GB
IN
InternVL3_5 30B A3B
Internvl · bartowski
Params30.5B
Context40K
Best fitQ8_0 33.8 GB
SE
sexeh time testing
Sexeh · mradermacher
Params8B
Context128K
Best fitF16 17.6 GB
LL
harborwater_open-llama-3b-v2-wizard-evol-instuct-v2-196k
Llama · TheBloke
Params3.43B
Context2K
Best fitQ6_K 6.9 GB
GE
Gemma 4 E4B xReadable zhTW OCR v1
Gemma · xCloudinfo
Params7.46B
Context128K
Best fitQ4_K_M 7.2 GB
MO
moondream2
Moondream · moondream
Params1.42B
Context2K
Best fitF16 5.0 GB
WI
ehartford_wizard-vicuna-7b-uncensored
Wizard · TheBloke
Params6.74B
Context2K
Best fitQ8_0 12.0 GB
LY
MN 12B Lyra v4
Lyra · Lewdiculous
Params12.2B
Context1000K
Best fitBF16 26.3 GB
QW
DarkIdol Qwen3.8 27B v1.1
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ6_K 25.1 GB
RU
RusMind 4.7 Momentum
Rusmind · DICPlay
Params4.65B
Context128K
Best fitBF16 10.4 GB
QW
Qwen3.5-27B
Qwen · unsloth
Params27.3B
Context256K
Best fitQ8_K_XL 38.4 GB
MI
Codestral-22B-v0.1
Mistral · lmstudio-community
Params22.2B
Context32K
Best fitQ8_0 26.0 GB
0G
0GM 1.0 35B A3B 0427
mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
OL
OLMoE 1B 7B 0924 Instruct
OLMo · allenai
Params6.9B
Context4K
Best fitF16 15.4 GB
QW
PAW 27B X3.1
Qwen · lackonendes
Params4.86B
Context256K
Smallest0.7 GB
MI
Mistral Large Instruct 2411
Mistral · bartowski
Params123B
Context128K
Best fitIQ2_M 45.1 GB
DA
L3 Dark Planet 8B
Dark · DavidAU
Params8B
Context8K
Best fitQ6_K 8.2 GB
QW
Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled APEX
Qwen · mudler
Params34.7B
Context256K
Smallest14.3 GB
HE
Hemmingway 1 Uncensored Heretic
Hemmingway · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
OL
Olmo 3.1 32B Think
OLMo · bartowski
Params32.2B
Context64K
Best fitQ8_0 36.9 GB
SA
Saiga_Nemo_12B_Sft_M10_D16
Saiga · IlyaGusev
Params12.2B
Context1000K
Best fitBF16 26.3 GB
EX
EXAONE-4.0-1.2B
Exaone · LGAI-EXAONE
Params1.28B
Context64K
Best fitBF16 3.6 GB
GA
GameScaling 27B S3
Gamescaling · mradermacher
Params26.9B
Context256K
Best fitQ8_0 31.3 GB
IN
Ingot IX 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B
Nemotron · lmstudio-community
Params74B
Context256K
Best fitIQ2_XXS 34.3 GB
QW
qwen3.8 flash coder 26gb
Qwen · Jab1718
Params42.6B
Context256K
Best fitQ8_0 46.7 GB
DE
DeepSeek R1 0528 Qwen3 8B heretic
DeepSeek · richardyoung
Params8.2B
Context128K
Best fitQ8_0 10.4 GB
PA
MS3.2 PaintedFantasy Visage v2 33B
Paintedfantasy · bartowski
Params33.6B
Context128K
Best fitQ8_0 38.1 GB