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.
QW
Huihui Qwen3.8 Flash Next abliterated i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
BG
bge-base-en-v1.5
BGE · CompendiumLabs
Params109M
Context512
Best fitF32 1.2 GB
QW
Qwen3.5 4B
Qwen · bartowski
Params4.33B
Context256K
Best fitBF16 10.3 GB
QW
Qwen Image 2.1
Qwen · leejet
Params7.12B
Context—
Best fitQ8_0 9.1 GB
QW
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
GR
Granite 4.2 3B BE
Granite · taronaeo
Params3.66B
Context—
Best fitF32 16.9 GB
IM
Z Image Turbo
Image · leejet
Params6.15B
Context—
Best fitQ8_0 7.9 GB
GE
Gemma 4 E2B It
Gemma · bartowski
Params4.65B
Context128K
Best fitBF16 10.4 GB
PH
Phi 4 Mini Instruct
Phi · unsloth
Params3.84B
Context128K
Best fitBF16 9.3 GB
GE
Google_Gemma 4 12B It
Gemma · lmstudio-community
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
QW
Qwen3 Reranker 0.6B
Qwen · ggml-org
Params596M
Context40K
Best fitQ8_0 2.1 GB
MU
Muse Glimmer 30B
Muse · lmstudio-community
Params28B
Context128K
Best fitQ4_K_M 17.7 GB
QW
Qwen Image 2.1 Text Encoder Heretic
Qwen · pottokao
Params8.2B
Context256K
Best fitQ8_0 10.4 GB
GE
Gemma-3-4B-It
Gemma · unsloth
Params3.88B
Context128K
Best fitBF16 9.4 GB
TE
test model router download
Test · ggml-org
Params1M
Context2K
Best fitF16 0.5 GB
GE
Google_Gemma 4 26B A4B It Qat Q4_0 Unquantized
Gemma · lmstudio-community
Params25.2B
Context256K
Best fitQ4_0 23.0 GB
LT
LTX 2.3 uncensored v1.4 FP8
Ltx · ChrisColeTech
Params21B
Context128K
Best fitQ8_0 26.5 GB
BO
Bonsai-8B
Bonsai · prism-ml
Params8.2B
Context64K
Best fitQ1_0 2.9 GB
QW
Qwen3 32B Awq Compatible Instruct
Qwen · Qwen
Params32.8B
Context40K
Best fitQ8_0 37.5 GB
QW
Qwen2.5 0.5B Instruct
Qwen · bartowski
Params494M
Context32K
Best fitF16 1.6 GB
GE
gemma 7b
Gemma · google
Params8.54B
Context—
Smallest34.2 GB
GE
gemma 4 12B coder fable5 composer2.5 v1
Gemma · yuxinlu1
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
MI
MiniCPM V 4.7 1B
MiniCPM · openbmb
Params1.01B
Context256K
Best fitF16 2.9 GB
QW
Qwen3 0.6B
Qwen · bartowski
Params752M
Context32K
Best fitBF16 2.9 GB
GE
Gemma 4 E2B
Gemma · lmstudio-community
Params4.65B
Context128K
Best fitQ8_0 6.1 GB
EM
embeddinggemma-2
Embeddinggemma · ggml-org
Params271M
Context256K
Best fitBF16 2.7 GB
QW
Qwen3.5 4B
Qwen · SoAIHQ
Params4.33B
Context256K
Best fitQ8_0 6.2 GB
QW
Qwen3.5-4B
Qwen · unsloth
Params4.33B
Context256K
Best fitBF16 10.3 GB
SU
Supra2 100M Instruct
Supra · SupraLabs
Params101M
Context2K
Best fitF16 0.8 GB
DE
Deepseek-R1-Distill-Qwen-1.5B
DeepSeek · unsloth
Params1.78B
Context128K
Best fitBF16 4.3 GB