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
Qwen3.5 9B
Qwen · bartowski
Params9.2B
Context256K
Best fitBF16 20.0 GB
Vision
LA
Laguna XS 2.1
Laguna · poolside
Params33.4B
Context256K
Best fitQ4_K_M 22.1 GB
GGUF
LF
LFM2.5 24B A2B Uncensored
Lfm · AtomicChat
Params24B
Context128K
Best fitQ8_0 28.9 GB
ReasoningTool use
QW
Qwen2.5 Coder 14B Instruct AWQ
Qwen · Qwen
Params29B
Context128K
Best fitQ8_0 33.5 GB
Coding
QW
Qwen3Vl 2b Instruct
Qwen · Qwen
Params1.72B
Context256K
Best fitF16 4.9 GB
Vision
SP
Spark X2.6 4B
Spark · XHToken
Params4.45B
Context1024K
Q4_K_M3.5 GB
ReasoningTool use
AG
Agents A1 4B
Agents · InternScience
Params4.21B
Context256K
Best fitQ4_K_M 4.3 GB
Vision
GE
gemma 4 E2B it qat q4 0
Gemma · google
Params4.63B
Context128K
Best fitQ4_0 4.4 GB
Vision
QW
Qwen3.8 27B Uncensored
Qwen · azukivc
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
GGUF
QW
Qwen3.6 35B A3B
Qwen · bartowski
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
Vision
LL
Llama 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Best fitF16 7.9 GB
GGUF
LA
Laguna S 2.1 APEX
Laguna · Myric
Params118B
Context1024K
Smallest0.7 GB
ReasoningTool use
GE
gemma 4 26B A4B it qat
Gemma · unsloth
Params430M
Context128K
Best fitQ4_K_XL 15.8 GB
Vision
QW
Qwen3 1.7B Instruct
Qwen · Qwen
Params1.72B
Context40K
Best fitQ8_0 3.3 GB
GGUF
LF
LFM2.5-24B-A2B-Preview
Lfm · unsloth
Params24B
Context128K
Best fitQ8_0 28.7 GB
GGUF
QW
Qwen3.5-27B
Qwen · unsloth
Params27B
Context256K
Best fitQ8_K_XL 38.2 GB
Vision
SA
Sage A1.5 Q8 0
Sage · InternScience
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
CodingTool useVision
GR
Parable Granite 4.1 3B Claude Fable 5
Granite · AnkitAI
Params3.4B
Context128K
Best fitF16 8.0 GB
ReasoningTool use
LL
Llama-3.2-3B-Instruct
Llama · unsloth
Params3.21B
Context128K
Best fitF16 7.9 GB
GGUF
GR
Parable Granite 4.1 8B Claude Fable 5
Granite · AnkitAI
Params8.38B
Context128K
Best fitF16 18.6 GB
ReasoningTool use
QW
Qwen3.8 Flash Next Uncensored i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
ReasoningTool useVision
GE
gemma-4-E2B-it
Gemma · ggml-org
Params4.65B
Context128K
Best fitBF16 9.9 GB
Vision
QW
Qwen_Qwen3.5 4B
Qwen · lmstudio-community
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
Vision
QW
Qwen2.5 14B Instruct
Qwen · bartowski
Params14.8B
Context32K
Best fitF16 31.7 GB
GGUF
OR
Ornith 1.5 122B
Ornith · unsloth
Params125B
Context256K
Best fitQ2_K_XL 45.9 GB
Vision
BG
bge-small-en-v1.5
BGE · CompendiumLabs
Params33M
Context512
Best fitF32 0.8 GB
Embedding
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB
Nemotron · nvidia
Params74B
Context256K
Smallest22.0 GB
Vision
QW
Holo 3.1 35B A3B
Qwen · Hcompany
Params34.7B
Context256K
Best fitQ4_K_M 22.5 GB
Vision
TE
Ternary Bonsai 2 27B Uncensored Heretic
Ternary · OS-Software
Params27B
Context256K
Smallest5.9 GB
Vision
QW
Qwen3 Embedding 0.6b
Qwen · Qwen
Params596M
Context32K
Best fitF16 2.6 GB
Embedding

Other memory sizes

Keep browsing