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.
LI
LightOnOCR 3 4B
Lightonocr · prithivMLmods
Params4.21B
Context256K
Best fitBF16 10.0 GB
HA
Harrier Oss v1 0.6b
Harrier · mradermacher
Params596M
Context32K
Best fitF16 2.6 GB
AI
Airoboros L2 70b 2.2
Airoboros · TheBloke
Params69B
Context4K
Best fitQ4_K_M 44.6 GB
QW
Qwen3.8-27B
Qwen · Greatjedi
Params27B
Context256K
Best fitQ4_K 19.1 GB
QW
Qwen3 Omni 30B A3B Captioner
Qwen · presencesw
Params30.5B
Context64K
Best fitQ4_K_M 19.9 GB
DE
decider 4b
Decider · Mapika
Params4.2B
Context256K
Best fitBF16 10.0 GB
QW
Qwen3.8 9B Distill Uncensored Heretic
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ6_K 9.2 GB
QW
Huihui Qwen3 VL 8B Instruct Abliterated
Qwen · noctrex
Params8.19B
Context256K
Best fitBF16 18.1 GB
QW
Qwen3-Vl-2B-Thinking
Qwen · unsloth
Params1.72B
Context256K
Best fitBF16 4.9 GB
TR
Translategemma 4b It
Translategemma · SandLogicTechnologies
Params3.88B
Context128K
Best fitQ5_K_M 4.5 GB
RO
TheDrummer Rocinante XL 16B v1
Rocinante · bartowski
Params16.1B
Context128K
Best fitBF16 34.5 GB
QW
Qwen3.5 4B heretic imatrix
Qwen · FadedRedStar
Params334M
Context256K
Best fitQ5_K_M 4.6 GB
MA
Magnum v4 72b
Magnum · bartowski
Params72.7B
Context32K
Best fitQ4_K_S 47.1 GB
QW
Qwen3.8 27B abliterated MTP
Qwen · hotdogs
Params27B
Context256K
Best fitQ8_0 31.7 GB
QW
Qwen2.5 VL 3B Instruct
Qwen · mradermacher
Params3.09B
Context125K
Best fitF16 7.0 GB
XX
encoder
Xxl · chatpig
Params219M
Context512
Best fitF16 13.2 GB
ME
G4 MeroMero 26B A4B It Uncensored Heretic
Meromero · llmfan46
Params25.2B
Context256K
Best fitQ8_0 35.4 GB
OR
Ornith 1.5 9b Mtp
Ornith · protoLabsAI
Params456M
Context256K
Best fitBF16 20.0 GB
LY
Lythri 4B A2B
Lythri · bartowski
Params4.63B
Context128K
Best fitBF16 10.4 GB
MI
Huihui Mistral Small 3.2 24B Instruct 2506 Abliterated
Mistral · maerong3
Params23.6B
Context128K
Best fitQ4_K_M 16.2 GB
QW
Qwen3.5 35B A3B APEX
Qwen · mudler
Params34.7B
Context256K
Smallest13.3 GB
NE
NeoHorse-1-4B
Neohorse · TokenRhythm
Params4.21B
Context256K
Best fitBF16 10.0 GB
DE
WhiteRabbitNeo WhiteRabbitNeo V3 7B
Deephat · bartowski
Params7.62B
Context32K
Best fitBF16 16.2 GB
WI
ehartford_wizard-vicuna-13b-uncensored
Wizard · TheBloke
Params13B
Context2K
Best fitQ8_0 21.0 GB
LF
LiquidAI_LFM2.5 1.2B Instruct
Lfm · lmstudio-community
Params1.17B
Context125K
Best fitQ8_0 2.8 GB
GE
Gemma 4 12B HybridAgent
Gemma · mradermacher
Params11.9B
Context256K
Best fitQ6_K 23.2 GB
QW
Qwen3 32B Uncensored
Qwen · mradermacher
Params32.8B
Context40K
Best fitQ8_0 37.5 GB
QW
Qwen3 VL 8B Heretic Stable
Qwen · mradermacher
Params8.19B
Context256K
Best fitF16 18.1 GB
LL
Llama 3.2 8X4B MOE V2 Dark Champion Instruct uncensored abliterated 21B
Llama · DavidAU
Params20.9B
Context128K
Best fitQ8_0 23.8 GB
GL
Glm-4-9B-0414
GLM · unsloth
Params9.4B
Context32K
Best fitBF16 19.6 GB