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.
GP
Gpt Oss 20b
gpt-oss · bartowski
Params20.9B
Context128K
Best fitBF16 14.7 GB
QW
Qwen3.5 9B Heretic v2
Qwen · filvyb
Params8.95B
Context256K
Best fitBF16 19.5 GB
GE
ThinkingCap gemma 4 26B A4B it
Gemma · bottlecapai
Params25.2B
Context256K
Best fitQ8_0 35.4 GB
NE
NeoHorse-1-9B
Neohorse · TokenRhythm
Params8.95B
Context256K
Best fitBF16 19.5 GB
DE
deepseek-ai_deepseek-coder-6.7b-base
DeepSeek · TheBloke
Params6.74B
Context16K
Best fitQ8_0 12.0 GB
GR
Granite 4.1 3b
Granite · ibm-granite
Params3.4B
Context128K
Best fitBF16 8.0 GB
GL
GLM-4.7-Flash-Uncensored-HauhauCS-Balanced
GLM · HauhauCS
Params30B
Context198K
Best fitQ8_0 33.2 GB
SE
SenseNova 6.8 Code2Video GSQ RCO
Sensenova · OliviaRossi
Params26.9B
Context256K
Best fitIQ3_S 14.5 GB
SA
Sage A1.5 Sangreal ICE
Sage · gbuzhf
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
GE
gemma-2-27b-it
Gemma · bartowski
Params27.2B
Context8K
Best fitQ8_0 33.6 GB
JA
JackOD 9B Coder
Jackod · ManniX-ITA
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
DE
DeepSeek R1 Distill Qwen 14B Abliterated v2
DeepSeek · mradermacher
Params14.8B
Context128K
Best fitQ8_0 17.8 GB
MA
Maple Preview
Maple · deepgrove
Params20.2B
Context128K
Best fitTQ2_0 7.3 GB
DE
DeepSeek R1 Distill Qwen 14B Uncensored
DeepSeek · mradermacher
Params14.8B
Context128K
Best fitQ8_0 17.8 GB
GE
Huihui gemma 4 12B agentic fable5 abliterated
Gemma · huihui-ai
Params11.9B
Context256K
Best fitQ8_0 14.7 GB
GP
Gpt Oss 120b Uncensored
gpt-oss · mradermacher
Params117B
Context128K
Q4_K_M87.9 GB
QW
Qwen2.5 7B Instruct Uncensored
Qwen · mradermacher
Params7.62B
Context32K
Best fitF16 16.2 GB
QW
Qwen3.8 27B EfficientThink VAL APEX I MiniPlus V3
Qwen · IsValorum
Params27.3B
Context256K
Q4_K_M1.1 GB
QW
Qwen3.8-27B
Qwen · jrell
Params27.3B
Context256K
Best fitIQ4_XS 16.2 GB
QW
Qwen3.5 9B GLM5.1 Distill v1
Qwen · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
MI
cognitivecomputations_dolphin-2.7-mixtral-8x7b
Mistral · TheBloke
Params46.7B
Context32K
Best fitQ6_K 40.0 GB
JI
JiRackUltra_14b
Jirackultra · CMSManhattan
Params14.8B
Context128K
Q4_K_M9.0 GB
WI
Wicked Stuff 26B A4B v2.1 Final
Wicked · ReadyArt
Params25.2B
Context256K
Best fitQ8_0 35.4 GB
GE
Assistant
Gemma · RachidAR
Params420M
Context128K
Best fitF16 2.4 GB
IM
Impish_Bloodmoon_12B
Impish · SicariusSicariiStuff
Params12.2B
Context128K
Best fitQ8_0 14.9 GB
LA
latxa-13b-v1.2
Latxa · mradermacher
Params13B
Context4K
Best fitQ6_K 17.9 GB
QW
ThinkingCap Qwen3.8 27B
Qwen · bottlecapai
Params27.3B
Context256K
Smallest14.3 GB
HO
K2 Horizon 7B Heretic
Horizon · mradermacher
Params9B
Context512K
Best fitQ6_K 9.1 GB
QW
Qwen3 30B A3B
Qwen · lmstudio-community
Params30.5B
Context32K
Best fitQ8_0 33.8 GB
LU
L3-8B-Lunaris-v1
Lunaris · bartowski
Params8B
Context8K
Best fitF32 33.7 GB