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
QW
Models Qwen Qwen3 4B Thinking 2507
Qwen · MaziyarPanahi
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
MI
Mistral-Small-4-119B-2603
Mistral · unsloth
Params119B
Context1024K
Best fitIQ3_S 45.2 GB
Vision
QW
Abliterated
Qwen · criscar22
Params7.6B
Context32K
Q4_K_M4.7 GB
Coding
GE
gemma 4 26B A4B it uncensored
Gemma · TrevorJS
Params25.2B
Context256K
Best fitQ8_0 35.4 GB
GGUF
NE
NeoHorse-1-4B
Neohorse · ngquocvinh
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
ReasoningTool use
TI
Tinylaya For Testing
Tinylaya · ggml-org
Params90M
Context8K
Best fitQ8_0 0.7 GB
GGUF
TE
Swift Bonsai 2
Ternary · ukisai
Params27B
Context256K
Smallest5.9 GB
Reasoning
QW
Qwen3.8 27B Pi
Qwen · bartowski
Params27.3B
Context256K
Best fitQ8_0 31.8 GB
CodingReasoningTool use
SM
SmolVLM2 500M Video Instruct
Smolvlm · ggml-org
Params409M
Context8K
Best fitF16 1.7 GB
Vision
LF
Lfm2.5-8B-A1B
Lfm · unsloth
Params8.47B
Context125K
Best fitBF16 19.1 GB
GGUF
GE
gemma 4 26B A4B it heretic APEX
Gemma · mudler
Params25.2B
Context256K
Smallest13.0 GB
CodingVision
SM
SmolVLM 256M Instruct
Smolvlm · ggml-org
Params163M
Context8K
Best fitF16 1.0 GB
Vision
LF
Lfm2.5-Vl-3B
Lfm · unsloth
Params2.7B
Context125K
Best fitBF16 7.9 GB
Vision
OR
Ornith 1.5 122B UNCENSORED
Ornith · dealignai
Params125B
Context256K
Best fitIQ2_XXS 45.4 GB
Vision
QW
Abliterated MiMo V2.6 Distill Qwen 9B
Qwen · BoldingBuilds
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
GGUF
QW
Qwen3 VL 8B GLM 4.7 Flash Heretic Uncensored Thinking
Qwen · mradermacher
Params8.19B
Context256K
Best fitF16 18.1 GB
ReasoningRoleplayVision
QW
Qwen2.5 Math 7B Instruct
Qwen · bartowski
Params7.62B
Context4K
Best fitF16 16.2 GB
GGUF
MI
Ministral 3 3B Instruct 2512
Mistral · bartowski
Params3.43B
Context256K
Best fitBF16 8.2 GB
Vision
QW
Qwen3.5-4B-3D-Coder
Qwen · ccore
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
CodingReasoningTool use
QW
Qwen3.5 122B A10B
Qwen · bartowski
Params125B
Context256K
Best fitQ2_K 47.7 GB
Vision
WI
Wicked Tutu 31B v0.1
Wicked · ReadyArt
Params30.7B
Context256K
Best fitIQ3_XS 47.4 GB
Roleplay
CL
Clef Flash Heretic
Clef · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · mudler
Params34.7B
Context256K
Smallest14.3 GB
Vision
QW
Qwen3.8 27B abliterated cyber preview MTP
Qwen · hotdogs
Params27.3B
Context256K
Best fitQ6_K 25.1 GB
Tool useVision
LL
Llama Joycaption Beta One Hf Llava
Llama · mradermacher
Params8B
Context128K
Best fitF16 17.6 GB
Vision
TE
Offrail 27B Uncensored
Ternary · sudoingx
Params28.6B
Context256K
Smallest6.3 GB
GGUF
MI
MiniCPM-V-4.7-35B-A3B-Uncensored
MiniCPM · gbuzhf
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
Vision
GE
Gemma 4 12B Coder Fable5 Composer2.5 v1 Uncensored Heretic
Gemma · llmfan46
Params11.9B
Context256K
Best fitF16 37.2 GB
CodingReasoningVision
GE
gemma 4 E2B it uncensored
Gemma · TrevorJS
Params4.65B
Context128K
Best fitQ8_0 6.1 GB
GGUF
SA
Sage A1.5 APEX I MiniPlus V2.1
Sage · IsValorum
Params35.5B
Context256K
Smallest15.2 GB
ReasoningTool useVision

Other memory sizes

Keep browsing