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
Qwen2.5 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Best fitF16 16.2 GB
MI
s1 mini
Mini · superwhisper
Params752M
Context40K
Best fitF16 2.9 GB
SP
Spark X2.5 1.7B
Spark · XHToken
Params1.71B
Context1024K
Q4_K_M1.1 GB
NO
North-Mini-Code-1.0
North · unsloth
Params30.5B
Context488K
Best fitQ8_K_XL 34.5 GB
LI
Ling 3.0 Flash
Ling · AtomicChat
Params124B
Context128K
Q4_K_M75.3 GB
QW
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16
Qwen · HauhauCS
Params4.21B
Context256K
Best fitBF16 10.0 GB
QW
Qwen3-1.7B
Qwen · unsloth
Params1.72B
Context40K
Best fitBF16 4.9 GB
XX
T5 V1_1 Xxl
Xxl · city96
Params4.76B
Context512
Best fitF32 22.8 GB
QW
Qwen3 0.6B Instruct
Qwen · Qwen
Params596M
Context40K
Best fitQ8_0 2.1 GB
QW
Parable Qwen3 8B Claude Fable 5
Qwen · AnkitAI
Params8.2B
Context40K
Best fitF16 18.1 GB
GE
gemma 4 12B it qat
Gemma · unsloth
Params440M
Context256K
Best fitQ4_K_XL 8.3 GB
TE
Tess-4.5-27B
Tess · migtissera
Params27B
Context256K
Best fitQ8_0 31.3 GB
QW
Parable Qwen3 4B Claude Fable 5
Qwen · AnkitAI
Params4B
Context40K
Best fitF16 9.8 GB
MI
MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking
MiniCPM · GnLOLot
Params1.08B
Context128K
Best fitF16 2.9 GB
CA
Carbon 8B
Carbon · HuggingFaceBio
Params8.26B
Context32K
Best fitBF16 18.1 GB
QW
Huihui Qwen3.5 9B Abliterated
Qwen · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
QW
Swift 1.5 Qwen3.8 27B
Qwen · ukisai
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
BG
bge small en v1.5
BGE · unsloth
Params33M
Context512
Best fitF16 0.7 GB
MU
Muse Glimmer 30B
Muse · meta-models
Params27.9B
Context128K
Best fitQ4_K_XL 20.3 GB
QW
Qwen3-Vl-8B-Instruct
Qwen · unsloth
Params8.19B
Context256K
Best fitBF16 18.1 GB
AG
Agents A1 4B
Agents · InternScience
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
MX
mxbai-embed-large-v1
Mxbai · ChristianAzinn
Params334M
Context512
Q4_K_M0.2 GB
CA
Carbon 3B
Carbon · HuggingFaceBio
Params3.45B
Context32K
Best fitBF16 7.8 GB
LF
LFM2.5-24B-A2B
Lfm · LiquidAI
Params24B
Context128K
Best fitQ8_0 28.7 GB
FL
Flint Preview
Flint · unsloth
Params39.8B
Context256K
Best fitQ8_0 43.6 GB
MI
MiniCPM5 1B Claude Opus Fable5 Thinking
MiniCPM · GnLOLot
Params1.08B
Context128K
Best fitF16 2.9 GB
EX
Experiment26 7B passthrough 10slice
Experiment · babybirdprd
Params7B
Context—
Best fitQ4_K_M 0.5 GB
GE
gemma 4 26B A4B it qat q4 0
Gemma · google
Params25.2B
Context256K
Best fitQ4_0 23.0 GB
NE
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
Nemotron · ggml-org
Params31.6B
Context1024K
Best fitQ8_0 41.2 GB
GE
humanizer-12b
Gemma · jialinyyzz
Params11.9B
Context256K
Best fitBF16 37.2 GB