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
Qwen3.8-27B
Qwen · Weirdo333
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
GE
gemma4 E2B it qat Q4 unsloth heretic
Gemma · MobiusDevelopment
Params4.63B
Context128K
Q4_K_M3.4 GB
LL
nousresearch_yarn-llama-2-13b-128k
Llama · TheBloke
Params13B
Context128K
Best fitQ8_0 21.0 GB
SP
Spark X2.6 4B
Spark · abenzerps
Params4.11B
Context1024K
Best fitBF16 9.9 GB
LL
Linux Meta Llama
Llama · yun2022
Params8.03B
Context128K
Smallest8.5 GB
LL
nousresearch_yarn-llama-2-13b-64k
Llama · TheBloke
Params13B
Context64K
Best fitQ8_0 21.0 GB
GE
Gemma 3 1b It Abliterated
Gemma · bartowski
Params1B
Context32K
Best fitBF16 2.7 GB
GA
GameScaling 9B S3
Gamescaling · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
GE
Baihua Gemma4 E4B
Gemma · mradermacher
Params7.46B
Context128K
Best fitQ6_K 8.1 GB
GE
gemma 4 E4B it heretic
Gemma · saidutta69
Params7.46B
Context128K
Best fitF16 16.9 GB
D1
d1 3B
NANI-Nithin
Params2.7B
Context32K
Best fitBF16 7.9 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · Kondara
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
PY
ajibawa-2023_python-code-33b
Python · TheBloke
Params32.5B
Context2K
Best fitQ6_K 40.3 GB
QW
Qwen2.5 14B Instruct 1M
Qwen · bartowski
Params14.8B
Context986K
Best fitF16 31.7 GB
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
DA
Dans PersonalityEngine V1.3.0 24b
Dans · bartowski
Params23.6B
Context128K
Best fitQ8_0 26.9 GB
QW
Qwen3.8 27B Uncensored Heretic MTP UD
Qwen · codavidgarcia
Params27.3B
Context256K
Best fitQ5_K_XL 23.6 GB
DE
DeepSeek Coder V2 Lite Instruct Abliterated
DeepSeek · mradermacher
Params15.7B
Context160K
Best fitQ8_0 17.7 GB
GR
Granite 4.0 1b
Granite · ibm-granite
Params1.63B
Context128K
Best fitBF16 6.5 GB
QW
Qwen_Qwen3 VL 32B Instruct
Qwen · lmstudio-community
Params32.8B
Context256K
Best fitQ8_0 37.5 GB
AR
Arctic Text2SQL R1 7B
Arctic · mradermacher
Params7.62B
Context32K
Best fitF16 16.2 GB
GR
Granite 20b Code Instruct 8k
Granite · mradermacher
Params20B
Context8K
Best fitQ6_K 17.4 GB
QU
QuartetAnemoi 70B t0.0001
Quartetanemoi · backyardai
Params69B
Context32K
Best fitQ4_K_M 44.6 GB
LL
Llama xLAM 2 8b Fc R
Llama · Salesforce
Params8B
Context128K
Best fitF16 17.6 GB
MI
Devstral-Small-2505
Mistral · unsloth
Params23.6B
Context128K
Best fitQ8_K_XL 30.8 GB
IN
Ingot II 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
DA
Darwin 35B A3B Opus
Darwin · mradermacher
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
GR
Granite 8b Code Base 128k
Granite · mradermacher
Params8.05B
Context125K
Best fitQ6_K 8.3 GB
MI
Magidonia 24B v4.3
Mistral · TheDrummer
Params23.6B
Context128K
Best fitQ8_0 26.9 GB
QW
Qwen3.8-27B
Qwen · Aleks199999
Params27.3B
Context256K
Best fitQ8_0 41.5 GB