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
GL
Glm-4.1V-9B-Thinking
GLM · unsloth
Params9.4B
Context64K
Best fitBF16 19.6 GB
ReasoningVision
MI
Mistral NeMo 12B Abliterated
Mistral · mradermacher
Params12.2B
Context128K
Best fitQ8_0 14.9 GB
GGUF
FA
Falcon
Falcon · mradermacher
Params41.8B
Context2K
Best fitQ6_K 36.5 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B Abliterated
DeepSeek · mradermacher
Params8B
Context128K
Best fitQ6_K 8.2 GB
Reasoning
QW
Qwen3 Omni 30B A3B Captioner
Qwen · mradermacher
Params30.5B
Context64K
Best fitQ6_K 26.4 GB
GGUF
PH
phi 2 electrical engineering
Phi · TheBloke
Params2.78B
Context2K
Best fitQ8_0 6.1 GB
GGUF
GR
granite 20b code instruct i1
Granite · mradermacher
Params20B
Context8K
Best fitQ6_K 17.4 GB
CodingTool use
TE
Ternary-Bonsai-2-27B-Uncensored
Ternary · gaston-parravicini
Params27B
Context256K
Smallest7.1 GB
Reasoning
GU
GUI Owl 1.5 2B Instruct
Gui · mradermacher
Params1.72B
Context32K
Best fitF16 4.9 GB
Vision
MP
Mpt 7b Storywriter
Mpt · mradermacher
Params6.65B
Context64K
Best fitQ6_K 10.3 GB
GGUF
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · mlabonne
Params8B
Context128K
Best fitBF16 17.6 GB
Tool use
CO
codegeex4-all-9b
Codegeex · legraphista
Params9.4B
Context128K
Best fitBF16 19.6 GB
GGUF
QW
Qwen Image 2.1 Text Encoder Heretic DHQ
Qwen · pottokao
Params8.2B
Context256K
Best fitQ4_K_M 6.7 GB
CodingVision
QW
Qwen3 1.7B Abliterated
Qwen · bartowski
Params1.72B
Context40K
Best fitBF16 4.9 GB
GGUF
NO
Nous Capybara limarpv3 34B i1
Nous · mradermacher
Params34.4B
Context195K
Best fitQ6_K 31.3 GB
GGUF
LI
Linne Oak 1 0
Linne · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
Tool useVision
QW
Qwen2.5 72B Instruct
Qwen · ThomasBaruzier
Params72.7B
Context32K
Best fitQ4_K_S 47.1 GB
GGUF
SO
Solar Open 100B
Solar · mradermacher
Params103B
Context128K
Best fitQ3_K_S 46.6 GB
GGUF
PA
PaddleOCR-VL-1.6
Paddleocr · Mungert
Params467M
Context128K
Best fitBF16 1.6 GB
Vision
TE
Ternary Bonsai 2 27B MTP
Ternary · ManniX-ITA
Params27.3B
Context256K
Smallest6.4 GB
GGUF
QW
Huihui Qwen3 30B A3B Thinking 2507 Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ8_0 33.8 GB
Reasoning
NE
neutts air q4
Neutts · neuphonic
Params748M
Context—
Best fitQ4_0 1.1 GB
GGUF
PA
Pantheon Reasoning 27B
Pantheon · bartowski
Params27.3B
Context256K
Best fitQ8_0 31.8 GB
ReasoningRoleplay
QW
EUAIAct Qwen2.5 0.5B Edge
Qwen · sallani
Params494M
Context32K
Best fitQ4_K_M 1.0 GB
GGUF
GE
Gemma 4 26B A4B
Gemma · mradermacher
Params25.2B
Context256K
Best fitQ8_0 35.4 GB
Vision
IN
InternVL3 1B Instruct
Internvl · ggml-org
Params630M
Context32K
Best fitF16 1.9 GB
Vision
HU
Hunyuan-A13B-Instruct
Hunyuan · unsloth
Params80B
Context256K
Best fitQ4_K_S 47.4 GB
GGUF
PY
Pythia 12b Deduped
Pythia · mradermacher
Params11.8B
Context2K
Best fitQ6_K 16.3 GB
GGUF
ST
L3 8B Stheno v3.2
Stheno · QuantFactory
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
KE
Kev-27B Artemis 12.3GB
Kev · turintech
Params25.6B
Context256K
Best fitQ4_K_S 17.2 GB
ReasoningTool use

Other memory sizes

Keep browsing