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 · LxBarn
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
DE
Deepseeker Kunou Qwen2.5 14b i1
DeepSeek · mradermacher
Params14.8B
Context128K
Best fitQ6_K 14.2 GB
LF
LFM2.5 24B A2B Uncensored
Lfm · pottokao
Params24B
Context128K
Best fitQ4_K_M 17.7 GB
GE
Genz 70b
Genz · TheBloke
Params69B
Context4K
Best fitQ4_K_M 44.6 GB
QW
Qwopus3.5 27B v3 Abliterated
Qwopus · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
ZW
ZwZ2 4B
Zwz · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
QW
Qwen2.5 Coder 3B Instruct
Qwen · bocalan
Params3.09B
Context32K
Best fitQ4_K_M 2.7 GB
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · bartowski
Params8B
Context128K
Best fitF32 33.7 GB
MI
Pixtral
Mistral · ggml-org
Params12.2B
Context1000K
Best fitF16 26.3 GB
LL
Meta-Llama-3-8B-Instruct-abliterated-v3
Llama · legraphista
Params8B
Context8K
Best fitBF16 17.6 GB
MI
kolibri-vikhr-mistral-0427
Mistral · Vikhrmodels
Params7.6B
Context32K
Best fitQ8_0 9.7 GB
MI
Mistral Small 4 119B 2603 Heretic
Mistral · Rioky
Params119B
Context1024K
Best fitQ2_K 44.2 GB
OR
ddh0_orcamaidxl-17b-32k
Orcamaidxl · TheBloke
Params17.5B
Context32K
Best fitQ8_0 28.1 GB
MI
mlabonne_neuralhermes-2.5-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
MI
MiniCPM V 4.7 35B A3B
MiniCPM · bartowski
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
TR
Trida2.0 4B
Trida · mradermacher
Params4.84B
Context256K
Best fitQ6_K 5.6 GB
EU
EuroLLM 9B Instruct
Eurollm · bartowski
Params9.15B
Context4K
Best fitF16 20.2 GB
QW
Qwen2.5 32B AGI
Qwen · mradermacher
Params32.8B
Context32K
Best fitQ6_K 29.5 GB
LL
LLaMA2 13B Tiefighter i1
Llama · mradermacher
Params13B
Context4K
Best fitQ6_K 17.9 GB
WI
ehartford_wizardlm-7b-v1.0-uncensored
Wizardlm · TheBloke
Params6.74B
Context2K
Best fitQ8_0 12.0 GB
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Best fitF16 10.0 GB
PI
piano-medley-7b
Piano · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
DI
discoresearch_discolm-70b
Discolm · TheBloke
Params69B
Context8K
Best fitQ4_K_M 44.6 GB
OR
Ornith 1.5 35B A3B uncensored
Ornith · ressl
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
AM
AMALIA 9B 0626 SFT
Amalia · NoxNotreve
Params9.15B
Context32K
Best fitBF16 20.2 GB
GR
Granite 34b Code Instruct 8k
Granite · RichardErkhov
Params33.7B
Context8K
Best fitQ8_0 36.9 GB
RW
rwitz_go-bruins-v2
Rwitz · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
FR
FrogNano 4B 2609
Frognano · NANI-Nithin
Params4.33B
Context256K
Best fitBF16 10.3 GB
GE
gemma 4 26B A4B it qat uncensored heretic UDmerge
Gemma · EZForever
Params25.2B
Context256K
Best fitQ4_K 22.9 GB
JA
Jais-3-MoVA-36B-A4B
Jais · mradermacher
Params37.4B
Context512K
Best fitQ6_K 32.9 GB