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
JI
jinen-v1-xsmall-hf
Jinen · togatogah
Params36M
Context1K
Best fitF16 0.7 GB
GGUF
LL
ggml llava v1.5 7b
LLaVA · mys
Params6.74B
Context4K
Best fitF16 18.3 GB
Vision
PH
phi3.5 gutenberg 4B
Phi · bartowski
Params3.82B
Context128K
Best fitF16 11.4 GB
GGUF
SE
Sexpedition MS3.2 24B
Sexpedition · mradermacher
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
GGUF
LI
Ling 3.0 tiny abliterated APEX
Ling · SC117
Params7.9B
Context128K
Best fitBF16 20.7 GB
GGUF
CO
Confucius4 R2T2
Confucius · netease-youdao
Params1.72B
Context64K
Best fitF16 4.9 GB
Vision
QW
Qwen3.8 27B Abliterated MTP
Qwen · GCSA-AiLab
Params27B
Context256K
Best fitQ8_0 31.3 GB
Vision
TE
Ternary Bonsai 1.7B
Ternary · prism-ml
Params1.72B
Context32K
Best fitF16 4.9 GB
GGUF
QW
Huihui Qwen3 8B Abliterated v2
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ6_K 8.4 GB
GGUF
DE
deepseek-ai_deepseek-coder-33b-base
DeepSeek · TheBloke
Params33.3B
Context16K
Best fitQ8_0 38.0 GB
Coding
DA
L3 Dark Planet 8B
Dark · DavidAU
Params8B
Context8K
Best fitQ8_0 11.1 GB
Roleplay
GE
Gemma 4 26B A4B It Uncensored
Gemma · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
ReasoningTool use
QW
Qwen3.8 27B Uncensored
Qwen · AtomicChat
Params27.3B
Context256K
Best fitQ8_0 31.6 GB
ReasoningTool useVision
PH
phi 4
Phi · unsloth
Params14.7B
Context16K
Best fitF16 31.5 GB
Coding
ST
stablelm 2 zephyr 1 6b
Stablelm · stabilityai
Params1.64B
Context4K
Smallest1.0 GB
GGUF
QW
Qwen2.5 VL 7B Abliterated Caption It
Qwen · mradermacher
Params7.62B
Context125K
Best fitF16 16.2 GB
Vision
QW
Qwen3.6 35B A3B heretic moe balanced v2
Qwen · DmitryDB
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
GGUF
LL
Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps
Llama · NousResearch
Params3.21B
Context128K
Best fitQ8_0 4.9 GB
RoleplayTool use
MI
dolphin 2.9.3 mistral nemo 12b
Mistral · dphn
Params12.2B
Context1000K
Best fitF16 26.3 GB
CodingTool use
QW
Qwen3 VL Reranker 8B
Qwen · mradermacher
Params8.19B
Context256K
Best fitF16 18.1 GB
EmbeddingVision
OL
ollama3.1
Ollama · xzlinuxmodels
Params8B
Context128K
Best fitBF16 17.6 GB
GGUF
OR
Ornith1.0 9B 3MPER0RR Abliterated
Ornith · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
ReasoningTool use
AR
Artemis 31B v1.1
Artemis · bartowski
Params30.7B
Context256K
Best fitIQ3_M 47.8 GB
Vision
ON
OneJev 4B
Onejev · mradermacher
Params4.84B
Context256K
Best fitF16 11.3 GB
Vision
QW
Qwen3.6 35B A3B
Qwen · byteshape
Params34.7B
Context256K
Best fitQ4_K_S 19.5 GB
Vision
QW
Qwopus GLM 18B Merged
Qwen · KyleHessling1
Params15.9B
Context256K
Best fitQ8_0 19.5 GB
ReasoningTool use
QW
Models Qwen Qwen2 Math 72B Instruct
Qwen · MaziyarPanahi
Params72.7B
Context4K
Best fitQ4_K_S 47.1 GB
GGUF
JE
JEV 27B VL Uncensored
Jev · mradermacher
Params27B
Context256K
Best fitQ8_0 31.2 GB
Vision
LF
LFM2.5 VL 3B Uncensored
Lfm · SC117
Params2.7B
Context125K
Best fitBF16 7.9 GB
Vision
HE
Hemmingway 1 Abliterated Extreme
Hemmingway · JohnDi
Params27B
Context256K
Best fitQ8_0 31.2 GB
Roleplay

Other memory sizes

Keep browsing