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.
AI
Airoboros L2 70B 2.1
Airoboros · TheBloke
Params69B
Context4K
Best fitQ4_K_M 44.6 GB
JA
stabilityai_japanese-stablelm-instruct-gamma-7b
Japanese · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
silicon based girlfriend v2
Qwen · RX5950XT
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
QW
Qwen3.8 27B uncensored
Qwen · ressl
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
SA
Sage A1.5
Sage · mradermacher
Params35.5B
Context256K
Best fitQ6_K 30.4 GB
GL
Glistening Gem 31B v2.1
Glistening · bartowski
Params30.7B
Context256K
Best fitIQ3_M 47.8 GB
CO
Yi Coder 9B Chat
Coder · mradermacher
Params8.83B
Context128K
Best fitQ6_K 8.6 GB
GL
Glm 4 9b Chat
GLM · bartowski
Params9.4B
Context128K
Best fitF16 19.6 GB
LU
G4 LuneLight 31B
Lunelight · zerofata
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
QW
Qwen2.5 7B Instruct 1M
Qwen · bartowski
Params7.62B
Context986K
Best fitF32 31.4 GB
GR
Granite-4.1-3B
Granite · unsloth
Params3.4B
Context128K
Best fitBF16 8.0 GB
QW
Darrellbest Qwen Image 2.1 PE I2I Heretic
Qwen · darrellbest
Params8.95B
Context256K
Best fitBF16 19.5 GB
SH
Shadow Siren 14B Pruned
Shadow · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
MI
llava 1.6 mistral 7b
Mistral · cjpais
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
Huihui Qwen3.5 4B Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
GE
Wanabi Gemma4 31B
Gemma · kawaimasa
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
NU
nuextract 1.5 tiny mealie ingredient parser
Nuextract · abyrne55
Params494M
Context32K
Best fitQ8_0 1.1 GB
RW
rwkv 6 world 3b
Rwkv · latestissue
Params3.1B
Context1024K
Best fitF32 14.4 GB
YA
YandexGPT 5 Lite 8B Instruct
Yandexgpt · yandex
Params8B
Context32K
Best fitQ4_K_M 6.5 GB
WH
whiterabbitneo_whiterabbitneo-33b-v1
Whiterabbitneo · TheBloke
Params33.3B
Context16K
Best fitQ8_0 38.0 GB
QW
Qwen3.8-27B
Qwen · k1lliiviie
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
OR
Ornith 1.5 35B A3B Heretic MTP APEX GSQ RCO
Ornith · lavendercomputing
Params447M
Context256K
Best fitIQ3_S 16.8 GB
CE
MN 12B Celeste V1.9
Celeste · bartowski
Params12.2B
Context1000K
Best fitF16 26.3 GB
LL
OrionStar-Yi-34B-Chat-Llama
Llama · mradermacher
Params34.4B
Context4K
Best fitQ6_K 30.7 GB
CY
Cydonia 24B v4.2.0
Cydonia · bartowski
Params23.6B
Context128K
Best fitQ8_0 26.9 GB
DO
dots.ocr
Dots · ggml-org
Params1.78B
Context128K
Best fitF16 4.3 GB
QW
Qwen3.8 Flash Next FLE
Qwen · sirfyyn
Params177B
Context256K
Best fitIQ4_NL 2.9 GB
MI
Mistral Small 24B Instruct 2501
Mistral · bartowski
Params23.6B
Context32K
Best fitQ8_0 26.9 GB
QW
Huihui Qwen3.6 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
CR
Creative Quants
Creative · drakira
Params11.9B
Context256K
Smallest8.6 GB