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.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · LxBarn
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
Vision
DE
Deepseeker Kunou Qwen2.5 14b i1
DeepSeek · mradermacher
Params14.8B
Context128K
Best fitQ6_K 14.2 GB
GGUF
LF
LFM2.5 24B A2B Uncensored
Lfm · pottokao
Params24B
Context128K
Best fitQ4_K_M 17.7 GB
ReasoningTool use
GE
Genz 70b
Genz · TheBloke
Params69B
Context4K
Best fitQ4_K_M 44.6 GB
GGUF
QW
Qwopus3.5 27B v3 Abliterated
Qwopus · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
Reasoning
ZW
ZwZ2 4B
Zwz · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
ReasoningTool use
QW
Qwen2.5 Coder 3B Instruct
Qwen · bocalan
Params3.09B
Context32K
Best fitQ4_K_M 2.7 GB
Coding
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · bartowski
Params8B
Context128K
Best fitF32 33.7 GB
Tool use
MI
Pixtral
Mistral · ggml-org
Params12.2B
Context1000K
Best fitF16 26.3 GB
Vision
LL
Meta-Llama-3-8B-Instruct-abliterated-v3
Llama · legraphista
Params8B
Context8K
Best fitBF16 17.6 GB
GGUF
MI
kolibri-vikhr-mistral-0427
Mistral · Vikhrmodels
Params7.6B
Context32K
Best fitQ8_0 9.7 GB
GGUF
MI
Mistral Small 4 119B 2603 Heretic
Mistral · Rioky
Params119B
Context1024K
Best fitQ2_K 44.2 GB
Vision
OR
ddh0_orcamaidxl-17b-32k
Orcamaidxl · TheBloke
Params17.5B
Context32K
Best fitQ8_0 28.1 GB
GGUF
MI
mlabonne_neuralhermes-2.5-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
Tool use
MI
MiniCPM V 4.7 35B A3B
MiniCPM · bartowski
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
Vision
TR
Trida2.0 4B
Trida · mradermacher
Params4.84B
Context256K
Best fitQ6_K 5.6 GB
ReasoningTool use
EU
EuroLLM 9B Instruct
Eurollm · bartowski
Params9.15B
Context4K
Best fitF16 20.2 GB
GGUF
QW
Qwen2.5 32B AGI
Qwen · mradermacher
Params32.8B
Context32K
Best fitQ6_K 29.5 GB
GGUF
LL
LLaMA2 13B Tiefighter i1
Llama · mradermacher
Params13B
Context4K
Best fitQ6_K 17.9 GB
GGUF
WI
ehartford_wizardlm-7b-v1.0-uncensored
Wizardlm · TheBloke
Params6.74B
Context2K
Best fitQ8_0 12.0 GB
GGUF
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Best fitF16 10.0 GB
ReasoningTool use
PI
piano-medley-7b
Piano · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
DI
discoresearch_discolm-70b
Discolm · TheBloke
Params69B
Context8K
Best fitQ4_K_M 44.6 GB
Tool use
OR
Ornith 1.5 35B A3B uncensored
Ornith · ressl
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
Vision
AM
AMALIA 9B 0626 SFT
Amalia · NoxNotreve
Params9.15B
Context32K
Best fitBF16 20.2 GB
GGUF
GR
Granite 34b Code Instruct 8k
Granite · RichardErkhov
Params33.7B
Context8K
Best fitQ8_0 36.9 GB
Coding
RW
rwitz_go-bruins-v2
Rwitz · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
Roleplay
FR
FrogNano 4B 2609
Frognano · NANI-Nithin
Params4.33B
Context256K
Best fitBF16 10.3 GB
CodingVision
GE
gemma 4 26B A4B it qat uncensored heretic UDmerge
Gemma · EZForever
Params25.2B
Context256K
Best fitQ4_K 22.9 GB
Vision
JA
Jais-3-MoVA-36B-A4B
Jais · mradermacher
Params37.4B
Context512K
Best fitQ6_K 32.9 GB
Reasoning

Other memory sizes

Keep browsing