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.
FL
Recursive Flint
Flint · lmstudio-community
Params39.8B
Context256K
Best fitQ8_0 43.7 GB
QW
Qwen2.5 Coder 3B Instruct AWQ
Qwen · Qwen
Params3.4B
Context32K
Q4_K_M2.1 GB
QW
Qwen3.8 27B Humanlike Chat
Qwen · LessThanThreeAI
Params26.9B
Context256K
Best fitQ8_0 31.2 GB
GE
Gemma-3-270M-It
Gemma · unsloth
Params268M
Context32K
Best fitF16 1.2 GB
GE
Gemma-4-E2B-Uncensored-HauhauCS-Aggressive
Gemma · HauhauCS
Params4.65B
Context128K
Best fitQ8_K 6.1 GB
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
ME
Mellum2 12B A2.5B Instruct
Mellum · JetBrains
Params12.1B
Context128K
Best fitQ4_K_M 9.0 GB
GE
Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced
Gemma · HauhauCS
Params30.7B
Context256K
Q4_K_M18.7 GB
QW
Qwen2.5 Omni 3B
Qwen · ggml-org
Params3.4B
Context32K
Best fitF16 7.6 GB
GE
Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced
Gemma · HauhauCS
Params25.2B
Context256K
Best fitQ8_K 35.8 GB
QW
Qwen3.6-27B
Qwen · ggml-org
Params26.9B
Context256K
Best fitQ8_0 31.2 GB
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ6_K 26.4 GB
HE
Hermes 4 14B
Hermes · bartowski
Params14.8B
Context40K
Best fitBF16 31.4 GB
MI
Devstral-Small-2-24B-Instruct-2512
Mistral · unsloth
Params23.6B
Context384K
Best fitQ8_K_XL 30.8 GB
QW
Qwen3.5-9B
Qwen · unsloth
Params9.2B
Context256K
Best fitBF16 20.0 GB
BT
BTL 4 Compact
Btl · badtheorylabs
Params34.7B
Context256K
Best fitIQ2_XXS 11.1 GB
MU
Homura 30B
Muse · hyrelabs
Params28B
Context128K
Best fitQ4_K_M 17.9 GB
NE
Nemotron 3 Embed 1B Q4 K M
Nemotron · zenmagnets
Params1.14B
Context256K
Best fitQ4_K_M 1.8 GB
QW
Qwen3.6 35B A3B Uncensored Heretic Native MTP Preserved
Qwen · llmfan46
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
GR
grug 27b qat q4
Grug · ProCreations
Params27B
Context256K
Best fitQ4_K_M 19.2 GB
GE
Gemma 4 31B It Uncensored Heretic
Gemma · llmfan46
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
GE
Gemma 3 4b It
Gemma · ggml-org
Params3.88B
Context128K
Best fitF16 9.4 GB
NA
Nanbeige4.3 33B
Nanbeige · bartowski
Params33.1B
Context512K
Best fitQ8_0 37.4 GB
QW
Qwen3.5 9B Abliterated
Qwen · lukey03
Params8.95B
Context256K
Best fitF16 19.5 GB
CL
Clef-Flash
Clef · ggml-org
Params9.08B
Context256K
Best fitBF16 19.7 GB
MO
MOSS-Music-8B
Moss · nerualdreming
Params8.19B
Context40K
Best fitQ4_K_M 6.9 GB
GE
gemma 4 31B it qat
Gemma · unsloth
Params480M
Context128K
Best fitQ4_K_XL 19.9 GB
GR
Granite 4.0 1B BE
Granite · taronaeo
Params1.63B
Context—
Best fitF32 7.8 GB
GE
gemma-4-12B-it
Gemma · ggml-org
Params11.9B
Context256K
Best fitBF16 25.4 GB
QW
Qwen2.5 1.5B Instruct
Qwen · bartowski
Params1.54B
Context32K
Best fitF16 3.8 GB