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.

Most downloadedNewestLargestLongest contextSmallest
MU
Muse Glimmer 30B Abliterated
Muse · The-freezer
Params28B
Context128K
Best fitQ8_0 30.3 GB
Vision
MI
MiniCPM V 4.7 1B DSpark
MiniCPM · openbmb
Params214M
Context256K
Best fitF16 1.0 GB
Tool useVision
LL
Meta Llama 3.1 70B Instruct
Llama · lmstudio-community
Params70.6B
Context128K
Best fitQ4_K_M 45.7 GB
GGUF
LI
T lite it 2.1
Lite · t-tech
Params8.2B
Context40K
Best fitQ8_0 10.4 GB
GGUF
PA
MS3.2 PaintedFantasy v4.1 24B
Paintedfantasy · zerofata
Params23.6B
Context128K
Best fitQ8_0 26.9 GB
GGUF
HO
K2 Horizon 0.9B
Horizon · IFM
Params1.08B
Context128K
Best fitBF16 3.1 GB
Reasoning
QW
Qwen2.5 14B Instruct
Qwen · lmstudio-community
Params14.8B
Context32K
Best fitQ8_0 17.8 GB
GGUF
GL
Huihui GLM 4.7 Flash Abliterated
GLM · mradermacher
Params30B
Context198K
Best fitQ6_K 26.0 GB
GGUF
KO
Huihui Kolibri 1 BF16 Abliterated
Kolibri · huihui-ai
Params78B
Context256K
Best fitQ3_K 38.9 GB
Reasoning
LL
Hermes 3 Llama 3.1 8B
Llama · bartowski
Params8B
Context128K
Best fitF32 33.7 GB
RoleplayTool use
QW
Qwen3 14B Abliterated
Qwen · RootMonsteR
Params14.8B
Context40K
Best fitQ5_K_M 12.4 GB
Tool use
LA
Laguna-S-2.1
Laguna · unsloth
Params118B
Context256K
Best fitIQ3_XXS 46.4 GB
GGUF
QW
Qwen3.8 Flash Next IQ4 XS
Qwen · julianmb
Params177B
Context256K
Best fitQ8_0 5.5 GB
GGUF
QW
Suri Qwen 3.8 27B Companion
Qwen · SpaceTimee
Params27.3B
Context256K
Best fitQ8_K_XL 34.6 GB
Vision
OR
Ornith 1.5 35B A3B Heretic MTP APEX
Ornith · SC117
Params447M
Context256K
Smallest14.3 GB
ReasoningVision
AP
35B A3B
Apus · apus-ailab
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
GGUF
QW
Qwen3 Reranker 4B GGUF llama cpp
Qwen · Voodisss
Params4B
Context40K
Best fitF16 9.8 GB
Embedding
SM
Smollm3-3B
SmolLM · unsloth
Params3.08B
Context64K
Best fitBF16 7.3 GB
GGUF
NE
Nvidia-Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Nemotron · unsloth
Params31.6B
Context1024K
Best fitQ8_K_XL 42.9 GB
ReasoningVision
QW
Qwen2 VL 2B Instruct
Qwen · ggml-org
Params1.54B
Context32K
Best fitF16 3.8 GB
Vision
GP
Huihui Gpt Oss 20b BF16 Abliterated
gpt-oss · huihui-ai
Params20.9B
Context128K
Best fitF16 42.8 GB
GGUF
LL
4yo1 llama3 pre1 pre2 ds ins2 lora3
Llama · RichardErkhov
Params200M
Context—
Best fitQ3_K_L 5.5 GB
GGUF
GE
Gemma 4 31B It Heretic
Gemma · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
Coding
QW
Qwen3 ASR 1.7B
Qwen · unslothai
Params2.03B
Context64K
Best fitBF16 5.5 GB
Vision
QW
sakura-14b-qwen2.5-v1.0-iq4xs
Qwen · SakuraLLM
Params14.8B
Context128K
Smallest8.2 GB
GGUF
AL
Source Hf Aliceai T5 35b A0.6B
Aliceai · ngquocvinh
Params34.6B
Context128K
Best fitQ8_0 37.6 GB
Coding
QW
Qwen3 VL 8B NSFW Caption V4.5
Qwen · mradermacher
Params8.19B
Context256K
Best fitF16 18.1 GB
Tool useVision
QW
Huihui Qwen3 4B Abliterated v2
Qwen · mradermacher
Params4B
Context40K
Best fitF16 9.8 GB
GGUF
GL
GLM 5.3 Flash UNCENSORED mlx oQ4e DFlash2
GLM · Solstice-AI
Params1.17B
Context1024K
Best fitBF16 3.0 GB
Vision
QW
Qwen2.5 7B Instruct 1M
Qwen · lmstudio-community
Params7.62B
Context986K
Best fitQ8_0 9.1 GB
GGUF

Other memory sizes

Keep browsing