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.
GE
Gemma 4 E2B it LocalAI
Gemma · weareapexcreators
Params7.5B
Context128K
Best fitQ5_K_M 7.4 GB
GE
Gemma 3 1b It
Gemma · bartowski
Params1B
Context32K
Best fitBF16 2.7 GB
PI
PII Tracer
Pii · perplexity-ai
Params596M
Context32K
Best fitF16 2.6 GB
MI
open-orca_mistral-7b-openorca
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GE
Gemma4 12B Uncensored LocalAI
Gemma · weareapexcreators
Params11.9B
Context256K
Best fitQ4_K_M 20.8 GB
QW
Qwen3.8 3.6 27B blend
Qwen · JetBrains
Params27.3B
Context256K
Best fitQ5_K_M 20.2 GB
BO
Bonsai-27B
Bonsai · weareapexcreators
Params27B
Context256K
Best fitQ1_0 6.5 GB
CH
Chandra Ocr 2
Chandra · prithivMLmods
Params4.84B
Context256K
Best fitBF16 11.3 GB
MI
MiniCPM OCR 1.0
MiniCPM · openbmb
Params752M
Context256K
Best fitF16 2.4 GB
QW
Ingot genesis 27B Q2
Qwen · dendriteholdings
Params27B
Context256K
Smallest7.2 GB
QW
Qwen3 Zero Coder Reasoning V2 0.8B NEO EX
Qwen · DavidAU
Params816M
Context40K
Best fitF16 3.5 GB
GR
Granite Embedding 107m Multilingual
Granite · bartowski
Params107M
Context512
Best fitF16 0.8 GB
QW
Qwen 3.5 27B Derestricted
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · lmstudio-community
Params7.62B
Context128K
Best fitQ8_0 9.1 GB
QW
NasledieLab Qwen3.5 0.8B GPT 6 Astra Luna Fable 5.1 Opus 5.5 distill Karpy
Qwen · aemmeath
Params752M
Context256K
Best fitQ4_K_M 1.4 GB
QW
Qwen3.6 35B A3B Uncensored LocalAI
Qwen · weareapexcreators
Params34.7B
Context256K
Best fitIQ2_M 12.8 GB
GR
Granite-4.1-3B
Granite · weareapexcreators
Params3.4B
Context128K
Best fitQ5_K_M 3.6 GB
FL
flux 3 image klein pup
Flux · unsloth
Params8.95B
Context256K
Best fitBF16 19.5 GB
QW
Qwen3.5 27B WebNovel Writer Zh
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
MU
Muse-Glimmer-30B
Muse · AtomicChat
Params27.9B
Context128K
Best fitQ8_0 33.1 GB
QW
DeepSeek V4 Pro Qwen3.5 9B MTP Public 20260801 HF
Qwen · Jackrong
Params9.2B
Context256K
Best fitBF16 20.0 GB
QW
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Heretic
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
QW
Qwen3.8-27B
Qwen · weareapexcreators
Params27.3B
Context256K
Best fitQ2_K_XL 13.4 GB
IN
Index Translate 35B A3B preview
Index · IndexTeam
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
QW
Qwen3.5 27B WebNovel Writer zh
Qwen · wcn123
Params27B
Context256K
Best fitQ4_K_M 19.2 GB
NO
nomic-embed-text-v1
Nomic · nomic-ai
Params137M
Context2K
Best fitF32 1.3 GB
QU
R3GE Quen2.5 7B
Quen · JackFRost0703
Params7.62B
Context128K
Best fitQ4_K_M 5.7 GB
QW
Qwen3 4B Instruct Awq
Qwen · electricpipelines
Params4B
Context40K
Best fitQ4_K_M 4.2 GB
QW
Qwen3 30B A3B Abliterated
Qwen · mradermacher
Params30.5B
Context40K
Best fitQ8_0 33.8 GB
LL
Llama-3.1-8B-Instruct
Llama · unsloth
Params8B
Context128K
Best fitBF16 17.6 GB