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
WH
whiterabbitneo_whiterabbitneo-13b
Whiterabbitneo · TheBloke
Params13B
Context16K
Best fitQ8_0 21.0 GB
GGUF
AG
Agents A1 APEX
Agents · mudler
Params34.7B
Context256K
Smallest13.5 GB
Vision
LL
Llama 3.2 1B Instruct Uncensored
Llama · mradermacher
Params1.24B
Context128K
Best fitF16 3.2 GB
GGUF
OL
ollama3.2 flutter
Ollama · pavansn2000
Params3.21B
Context128K
Best fitQ8_0 4.9 GB
GGUF
QW
Qwen2.5 7B Instruct Uncensored
Qwen · QuantFactory
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
GGUF
GR
Granite 4.0 H Micro
Granite · ibm-granite
Params3.2B
Context1024K
Best fitBF16 9.6 GB
GGUF
GL
Glm-Z1-9B-0414
GLM · unsloth
Params9.4B
Context32K
Best fitBF16 19.6 GB
GGUF
QW
Qwen3.8 27B Abliterated GSQ Orca
Qwen · ayozhee
Params27.3B
Context256K
Best fitIQ3_S 14.8 GB
GGUF
QW
Qwen3.8 27B Fable Distill Heretic Ara
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ6_K 25.1 GB
GGUF
QW
Qwen3.8 27B EfficientThink VAL APEX I NanoPlus V3
Qwen · IsValorum
Params27.3B
Context256K
Q4_K_M1.1 GB
CodingReasoningTool use
BE
Behemoth 128B v3
Behemoth · bartowski
Params125B
Context256K
Best fitIQ2_XS 46.8 GB
GGUF
QW
Qwen2.5.1 Coder 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Best fitF16 16.2 GB
Coding
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B
Nemotron · darioooooo0o
Params74B
Context1024K
Best fitIQ3_XXS 42.7 GB
Vision
NE
Nvidia-Nemotron-3-Nano-4B
Nemotron · unsloth
Params3.97B
Context1024K
Best fitBF16 15.5 GB
GGUF
LL
Phind CodeLlama 34B v2
Llama · mradermacher
Params33.7B
Context16K
Best fitQ6_K 29.8 GB
Coding
QW
Qwen3.8 27B APEX
Qwen · mudler
Params27.3B
Context256K
Smallest11.2 GB
Vision
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB
Nemotron · BoldingBuilds
Params74B
Context256K
Smallest22.0 GB
Vision
DA
Dark Scarlett 27B v2.0
Dark · ReadyArt
Params27.3B
Context256K
Best fitQ8_0 34.1 GB
RoleplayVision
AP
APUS Reflex 4B
Apus · apus-ailab
Params4.2B
Context256K
Best fitBF16 10.0 GB
GGUF
LF
LFM2.5 24B A2B
Lfm · bartowski
Params24B
Context128K
Best fitQ8_0 28.7 GB
ReasoningTool use
DE
DeepSeek R1 0528 Qwen3 8B Abliterated
DeepSeek · noteventhrice
Params8.19B
Context128K
Best fitQ4_K_M 6.7 GB
ReasoningTool use
QW
Qwen3.6 27B MTP pi tune
Qwen · bytkim
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
CodingReasoningTool use
LA
Laguna XS 2.1
Laguna · bartowski
Params33.4B
Context256K
Best fitQ8_0 37.4 GB
GGUF
QW
Qwen3-Vl-8B-Thinking
Qwen · unsloth
Params8.19B
Context256K
Best fitBF16 18.1 GB
ReasoningVision
QW
Qwen3 VL 2B Instruct
Qwen · bartowski
Params1.72B
Context256K
Best fitBF16 4.9 GB
Vision
GE
Gemma 4 E2B It Heretic v1
Gemma · mradermacher
Params4.63B
Context128K
Best fitQ6_K 4.9 GB
Vision
QW
Qwen3.5 397B A17B
Qwen · bartowski
Params403B
Context256K
Best fitQ8_0 10.7 GB
Vision
VE
Veloxy Titan 32B Vision
Veloxy · mradermacher
Params26.9B
Context256K
Best fitQ6_K 24.7 GB
CodingReasoningVision
ON
OneJev 9B
Onejev · bartowski
Params8.95B
Context256K
Best fitBF16 19.5 GB
Vision
PA
Pantheon Reasoning 26B A4B 1.1 V2
Pantheon · bartowski
Params26B
Context256K
Best fitQ8_0 36.2 GB
ReasoningRoleplay

Other memory sizes

Keep browsing