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.
EM
Embeddinggemma 300m
Embeddinggemma · ente-ai
Params308M
Context2K
Best fitQ8_0 1.0 GB
GE
gemma-2-9b-it
Gemma · bartowski
Params9.24B
Context8K
Best fitF32 40.3 GB
OR
Ornith 1.5 35B A3B
Ornith · AtomicChat
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
GE
Gemma 3 12b It
Gemma · lmstudio-community
Params11.8B
Context128K
Best fitQ8_0 16.2 GB
LF
LFM3 1.7B Uncensored
Lfm · AtomicChat
Params1.73B
Context256K
Best fitQ6_K 3.7 GB
SE
Hermes 4_3_36b
Seed · NousResearch
Params36.2B
Context512K
Best fitQ8_0 41.1 GB
GL
GLM 4.7 Flash
GLM · ggml-org
Params30B
Context198K
Best fitQ8_0 33.2 GB
QW
QwQ 32B
Qwen · Qwen
Params32.8B
Context128K
Best fitQ8_0 37.5 GB
ME
G4 MeroMero 31B
Meromero · zerofata
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
MA
Magidonia 24B v4.3
Magidonia · bartowski
Params23.6B
Context128K
Best fitQ8_0 26.9 GB
QW
Huihui Qwable 3.6 27b abliterated MTP
Qwable · huihui-ai
Params27.3B
Context256K
Best fitQ4_K_M 30.4 GB
SA
Sao10K L3 8B Stheno v3.1
Sao · RichardErkhov
Params8B
Context—
Best fitIQ4_NL 5.8 GB
QW
Qwen2.5-Vl-3B-Instruct
Qwen · unsloth
Params3.09B
Context125K
Best fitBF16 7.0 GB
GL
GLM 4.7 Flash
GLM · bartowski
Params30B
Context198K
Best fitQ8_0 33.2 GB
GE
gemma 4 12B it
Gemma · AtomicChat
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
QW
Huihui Qwen3 30B A3B Instruct 2507 Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ6_K 26.4 GB
QW
Qwen3 Coder Next Abliterated
Qwen · bartowski
Params79.7B
Context256K
Best fitQ4_0 47.2 GB
BO
Bonsai-4B
Bonsai · prism-ml
Params4B
Context32K
Best fitQ1_0 2.3 GB
QW
Qwen3 14B Abliterated
Qwen · bartowski
Params14.8B
Context40K
Best fitBF16 31.4 GB
QW
Qwen3.5-27B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params27B
Context256K
Best fitQ8_0 31.2 GB
QW
Qwen3.8 9B Distill SLERP F451 Pro Writer Uncensored
Qwen · nuofang
Params1M
Context256K
Best fitQ8_0 11.1 GB
QW
Huihui Qwable 3.6 27b abliterated
Qwable · huihui-ai
Params27B
Context256K
Best fitQ4_K_M 29.6 GB
QW
Qwen Image Edit Rapid AIO
Qwen · Phil2Sat
Params7.62B
Context125K
Best fitF16 41.8 GB
QW
Atomic Chat / Qwen3.5 4B DFlash
Qwen · AtomicChat
Params634M
Context256K
Best fitQ8_0 1.4 GB
GE
gemma 4 E4B it
Gemma · AtomicChat
Params7.52B
Context128K
Best fitQ8_0 9.9 GB
QW
Models Qwen Qwen3 30B A3B Instruct 2507
Qwen · MaziyarPanahi
Params30.5B
Context256K
Best fitQ6_K 26.4 GB
TE
Ternary Bonsai 2 27B Abliterated PTQ1 0
Ternary · BoldingBuilds
Params26.9B
Context256K
Smallest5.9 GB
QW
Qwen3.5 122B A10B
Qwen · mradermacher
Params122B
Context256K
Best fitQ2_K 45.9 GB
QW
Atomic Chat / Qwen3 4B DFlash
Qwen · AtomicChat
Params537M
Context40K
Best fitQ8_0 1.2 GB
FL
Flint NVFP4 Preview
Flint · RecursiveSI
Params39.8B
Context256K
Smallest22.9 GB