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.
LL
dolphin 2.9 llama3 8b
Llama · bartowski
Params8B
Context8K
Best fitF16 17.6 GB
QW
Qwen3 0.6B Abliterated
Qwen · mradermacher
Params596M
Context40K
Best fitF16 2.6 GB
QW
Qwen3 0.6B Heretic Abliterated Uncensored
Qwen · mradermacher
Params596M
Context40K
Best fitQ5_K_S 1.9 GB
QW
Qwen3.8 27B GSQ RCO IQ3 XXS Uncensored
Qwen · RentedNoodle
Params27.3B
Context256K
Best fitIQ3_XXS 13.1 GB
FL
FLUX 3 Image Klein
Flux · AtomicChat
Params5.55B
Context256K
Best fitBF16 12.8 GB
MI
Ministral-3-8B-Instruct-2512
Mistral · unsloth
Params8.49B
Context256K
Best fitBF16 18.6 GB
CE
MN 12B Celeste V1.9
Celeste · nothingiisreal
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Qwen3 0.6B Heretic
Qwen · mradermacher
Params596M
Context40K
Best fitF16 2.6 GB
VI
VieNeu TTS v2
Vieneu · pnnbao-ump
Params294M
Context4K
Smallest0.2 GB
JE
JEV 27B VL
Jev · prithivMLmods
Params27B
Context256K
Best fitQ5_K_M 21.9 GB
SM
SmolLM2 360M Instruct
SmolLM · HuggingFaceTB
Params362M
Context8K
Best fitQ8_0 1.2 GB
QW
Qwen3.6 35B A3B Uncensored
Qwen · xCloudinfo
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
LL
Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps
Llama · bartowski
Params3.21B
Context128K
Best fitF32 14.3 GB
QW
Bahushruth Qwen3.6 35B A3B Abliterated v4
Qwen · Bahushruth
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
LI
Ling-3.0-tiny
Ling · inclusionAI
Params7.9B
Context128K
Best fitBF16 20.7 GB
QW
Qwen3 14B Abliterated Conservative
Qwen · richardyoung
Params14.8B
Context40K
Best fitF16 31.4 GB
QW
Qwen3 Next 80B A3B Instruct
Qwen · bartowski
Params80B
Context256K
Best fitQ4_0 47.4 GB
QW
Qwen3.5-2B
Qwen · unsloth
Params1.94B
Context256K
Best fitBF16 4.8 GB
NE
NVIDIA Nemotron 3 Nano 4B
Nemotron · nvidia
Params3.97B
Context1024K
Best fitQ4_K_M 10.4 GB
QW
Qwen_Qwen3.5 0.8B
Qwen · lmstudio-community
Params752M
Context256K
Best fitQ8_0 1.7 GB
HO
Holo4 27B
Holo · Hcompany
Params27B
Context256K
Best fitQ4_K_M 19.5 GB
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B
Nemotron · AtomicChat
Params32.9B
Context1024K
Best fitQ8_0 42.6 GB
QW
Z Image Qwen 3 4b text encoder
Qwen · worstplayer
Params4B
Context40K
Smallest2.1 GB
QW
Qwen2.5 VL 3B Instruct
Qwen · lmstudio-community
Params3.09B
Context125K
Best fitQ8_0 4.1 GB
LL
testmod koen llama2 13b dpotrain testver
Llama · RichardErkhov
Params13B
Context—
Best fitIQ3_M 7.2 GB
QW
Qwen3.6 35B A3B Uncensored HauhauCS MTP
Qwen · morikomorizz
Params447M
Context256K
Best fitQ8_K 45.7 GB
QW
Qwen3 8B Abliterated
Qwen · mradermacher
Params8.19B
Context40K
Best fitF16 18.1 GB
KI
Kimi Linear 48B A3B Instruct
Kimi · bartowski
Params49.1B
Context1024K
Best fitQ5_K_L 45.0 GB
QW
Qwen3 8B Hivemind Instruct Heretic Abliterated Uncensored NEO Imatrix
Qwen · DavidAU
Params7.66B
Context256K
Best fitQ8_0 11.1 GB
OR
Ornith 1.5 9B
Ornith · bartowski
Params8.95B
Context256K
Best fitBF16 19.5 GB