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.
QW
Qwen3 VL 8B Instruct
Qwen · bartowski
Params8.19B
Context256K
Best fitBF16 18.1 GB
QW
Atomic Chat / Qwen3.5 9B DFlash
Qwen · AtomicChat
Params1.29B
Context256K
Best fitQ8_0 2.1 GB
QW
Qwen3.6 35B A3B DFlash GGUF llama.cpp
Qwen · Alittlehammmer
Params386M
Context256K
Best fitBF16 1.5 GB
QW
Qwen3.6 27B A3B Coder
Qwen · ManniX-ITA
Params26.2B
Context256K
Best fitQ8_0 29.1 GB
QW
Qwen3 14B
Qwen · bartowski
Params14.8B
Context32K
Best fitBF16 31.4 GB
MI
Dolphin3.0 Mistral 24B
Mistral · bartowski
Params23.6B
Context32K
Best fitQ8_0 26.9 GB
GL
Glm-4.6V
GLM · unsloth
Params107B
Context128K
Best fitQ2_K_XL 47.8 GB
QW
Qwen2.5 14B Instruct Abliterated v2
Qwen · mradermacher
Params14.8B
Context32K
Best fitQ8_0 17.8 GB
QW
sakura-7b-qwen2.5-v1.0-iq4xs
Qwen · SakuraLLM
Params7.62B
Context128K
Smallest4.3 GB
BG
bge reranker v2 m3
BGE · gpustack
Params568M
Context8K
Q4_K_M0.4 GB
MI
Ministral-3-3B-Instruct-2512
Mistral · unsloth
Params3.43B
Context256K
Best fitBF16 8.2 GB
GL
Zai org_GLM 4.6V Flash
GLM · lmstudio-community
Params9.4B
Context128K
Best fitQ8_0 10.8 GB
CY
Blackfrost-AI/CYBER-FROST-3.8-BF16
Cyber · freakyskittle
Params177B
Context256K
Best fitQ8_0 5.5 GB
QW
Qwen_Qwen3 30B A3B Instruct 2507
Qwen · lmstudio-community
Params30.5B
Context256K
Best fitQ8_0 33.8 GB
QW
Huihui Qwen3.8 27B Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
QW
Qwen2.5 Math 1.5B Instruct
Qwen · bartowski
Params1.54B
Context4K
Best fitF16 3.8 GB
LF
LFM2.5 VL 1.6B
Lfm · ente-ai
Params1.17B
Context125K
Best fitBF16 3.9 GB
JE
JevK5
Jevk · alibiserikbay
Params1.88B
Context256K
Best fitQ8_0 11.1 GB
QW
Qwen2.5 7B Instruct
Qwen · lmstudio-community
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
VO
VoxCPM2
Voxcpm · DennisHuang648
Params912M
Context32K
Best fitF16 4.0 GB
MI
mistralai_Ministral 3 14B Reasoning 2512
Mistral · lmstudio-community
Params13.5B
Context256K
Best fitQ8_0 16.2 GB
QW
OrcaSAQ 2 Cyber 27B Uncensored
Qwen · orcarouter
Params27.3B
Context256K
Smallest15.7 GB
TE
Ternary Bonsai 2 27B Abliterated
Ternary · Hikari07jp
Params27B
Context256K
Smallest7.2 GB
QW
Qwen3 14B Uncensored
Qwen · mradermacher
Params14.8B
Context40K
Best fitQ8_0 17.5 GB
GE
Gemma 4 Novelist Eclipse 31B
Gemma · bartowski
Params32.1B
Context256K
Best fitQ3_K_S 47.6 GB
QW
SpaceTimee/Suri-Qwen-3.8-27B-Uncensored
Qwen · SpaceTimee
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
OR
Ornith 1.0 35B Heretic MTP APEX
Ornith · SC117
Params447M
Context—
Smallest0.2 GB
GE
UNSEEN Gemma 4 26B NSFW
Gemma · Jommarn
Params25.2B
Context256K
Best fitQ8_0 35.4 GB
VL
vllm-d3
ggml-org
Params26.9B
Context256K
Best fitQ8_0 31.2 GB
DE
DeepSeek R1 Distill Qwen 32B Abliterated
DeepSeek · bartowski
Params32.8B
Context128K
Best fitQ8_0 37.5 GB