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.
PA
PaddleOCR VL 1.6
Paddleocr · LunarOilRig
Params467M
Context128K
Best fitQ4_K_M 1.0 GB
HY
Hy-Mt2-7B
unsloth
Params7.5B
Context256K
Best fitBF16 16.6 GB
QW
Qwen3.6 35B A3B MTP APEX I MiniPlus V2.1 Abliterated
Qwen · IsValorum
Params34.7B
Context256K
Smallest1.2 GB
GE
Gemmasutra Mini 2B v1
Gemma · TheDrummer
Params2.61B
Context8K
Best fitF32 11.8 GB
QW
Qwen3.5-9B
Qwen · jc-builds
Params8.95B
Context256K
Best fitQ4_K_M 7.3 GB
QW
Qwen3-Coder-30B-A3B-Instruct-1M
Qwen · unsloth
Params30.5B
Context1024K
Best fitQ8_K_XL 37.3 GB
GE
google gemma 3 12b it qat q4 0 gguf small fix
Gemma · Dampfinchen
Params11.8B
Context128K
Best fitQ4_0 10.6 GB
QW
Huihui Qwen3.5 9B Abliterated
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
OR
Ornith 1.0 35B
Ornith · unsloth
Params34.7B
Context256K
Best fitQ8_K_XL 39.4 GB
QW
Huihui Qwen3.6 35B A3B abliterated
Qwen · Abiray
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
QW
Qwen3 8B
Qwen · Aldaris
Params8.19B
Context40K
Best fitQ4_K_M 6.7 GB
GE
Gemma 4 31B It Abliterated
Gemma · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
QW
Huihui Qwen3.8 27B Coder390 EfficientThink Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ6_K 25.1 GB
GE
Gemma 3 27b It
Gemma · bartowski
Params27B
Context128K
Best fitQ8_0 33.4 GB
QW
Qwen2.5 14B
Qwen · bartowski
Params14.8B
Context128K
Best fitF16 31.7 GB
QW
Qwen3.6 12B IQ Ultra Heretic Uncensored Thinking V2 Hightop
Qwen · KevinJK51
Params11.7B
Context256K
Best fitQ8_0 13.7 GB
QW
Qwen3.8 27B Uncensored
Qwen · xCloudinfo
Params26.9B
Context256K
Best fitQ8_0 31.2 GB
PH
phi 4
Phi · microsoft
Params14.7B
Context16K
Best fitBF16 31.5 GB
LA
latxa-7b-v1.2
Latxa · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
GE
gemma 4 E4B it heretic
Gemma · Abiray
Params7.5B
Context128K
Best fitQ8_0 9.9 GB
AP
APUS Reflex 9B
Apus · apus-ailab
Params8.95B
Context256K
Best fitBF16 19.5 GB
MI
mistralai_mistral-7b-v0.1
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GE
Gemma 4 31B Fable Coder
Gemma · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
MI
Mistral Nemo Instruct 2407 12B Thinking M Claude Opus High Reasoning
Mistral · mradermacher
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
GR
TwIL LM3 Pro
Granite · webAI-Official
Params3.66B
Context128K
Best fitF16 8.5 GB
SO
Sommerfugl 31b v2
Sommerfugl · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
HE
Hemmingway 1
Hemmingway · botp
Params27.3B
Context256K
Best fitQ8_0 31.8 GB
QW
Qwen1.5-0.5B-Chat-AWQ-fp16
Qwen · Qwen
Params620M
Context32K
Best fitQ8_0 2.0 GB
HU
HunyuanOCR
Hunyuanocr · prithivMLmods
Params539M
Context128K
Best fitF32 3.5 GB
QW
Qwen3.8 Distill 35B A3B Coder Abliterated
Qwen · Lord-H4D3ZS
Params35.5B
Context256K
Smallest12.3 GB