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
Qwen3.5 2B Uncensored Abliterix SOM
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
QW
Qwen3.6 35B A3B APEX MTP Strata Q5EXPS
Qwen · misthemAI
Params35.5B
Context256K
Smallest22.5 GB
MI
nousresearch_nous-hermes-2-mixtral-8x7b-dpo
Mistral · TheBloke
Params46.7B
Context32K
Best fitQ6_K 40.0 GB
QW
Qwen3.8 Flash Next REAM 60Pct
Qwen · RemySkye
Params129B
Context256K
Best fitQ3_K_L 36.9 GB
CO
Yi Coder 1.5B Chat
Coder · bartowski
Params1.48B
Context128K
Best fitF16 5.1 GB
DE
DeepSeek R1 Distill Llama 8B Abliterated
DeepSeek · mradermacher
Params8B
Context128K
Best fitF16 17.6 GB
NO
North Mini Code 1.0
North · bartowski
Params30.5B
Context488K
Best fitQ8_0 33.8 GB
MI
MiniCPM5 2B Abliterated Uncensored
MiniCPM · mondk
Params2.52B
Context128K
Best fitF16 5.9 GB
QW
Qwen3.8 2B Uncensored
Qwen · atakhadivi
Params1.88B
Context256K
Best fitQ4_K_M 2.2 GB
GP
GPT OSS 20B Uncensored HauhauCS Aggressive
gpt-oss · HauhauCS
Params20.9B
Context128K
Best fitMXFP4 13.0 GB
OC
Occamy 1.0 APEX I MiniPlus V2.1 Abliterated
Occamy · IsValorum
Params34.7B
Context256K
Q4_K_M1.3 GB
QW
Qwen3.8 27B Coder390 EfficientThink abliterated ROCmFPX
Qwen · ArtomYuan
Params27.3B
Context256K
Best fitQ8_0 31.3 GB
GL
GLM 5.3 Flash UNCENSORED NVFP4 DFlash2
GLM · Solstice-AI
Params1.17B
Context1024K
Best fitBF16 3.0 GB
QW
Swift-1.5-Qwen3.8-27B-Uncensored-MTP
Qwen · IsValorum
Params27.3B
Context256K
Smallest12.2 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · lmstudio-community
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
OP
openjev
Openjev · openjev
Params27B
Context256K
Best fitQ8_0 31.2 GB
PH
phi 4
Phi · lmstudio-community
Params14.7B
Context16K
Best fitQ8_0 17.8 GB
PH
Phi 3 mini 4k instruct update2024 07 03 IMat
Phi · legraphista
Params3.82B
Context4K
Best fitBF16 11.4 GB
WI
Wingless_Imp_8B
Wingless · mradermacher
Params8B
Context128K
Best fitF16 17.6 GB
MI
Rocinante XL 16B v1
Mistral · TheDrummer
Params16.1B
Context128K
Best fitQ8_0 19.4 GB
MI
MiniCPM OCR Jev
MiniCPM · openbmb
Params1.88B
Context256K
Best fitF16 4.7 GB
LI
vllm-d3-lite
Lite · ggml-org
Params1.01B
Context256K
Best fitBF16 2.9 GB
AE
AesCode 32B
Aescode · bartowski
Params32.8B
Context256K
Best fitQ8_0 37.5 GB
DA
Darwin 27B RSI
Darwin · bartowski
Params27B
Context256K
Best fitQ8_0 31.3 GB
QW
Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params4B
Context256K
Q4_K_M2.5 GB
GE
Gemma 3 27b It
Gemma · lmstudio-community
Params27B
Context128K
Best fitQ8_0 33.4 GB
GE
Ablation 187 Gemma3.Webnovels.Test.Gemma 3 4b
Gemma · mradermacher
Params3.88B
Context128K
Best fitF16 9.4 GB
GR
Granite 4.0 Micro
Granite · ibm-granite
Params3.4B
Context128K
Best fitBF16 10.7 GB
NE
Nex N2.5 mini
Nex · abenzerps
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
QW
Qwen3.5 9B Heretic v2
Qwen · AIImageStudio
Params8.95B
Context256K
Best fitQ8_0 11.1 GB