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
Qwen3.5-2B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params1.88B
Context256K
Best fitBF16 4.7 GB
QW
Qwen3.8 14B Instruct Turbo
Qwen · mradermacher
Params14.7B
Context256K
Best fitQ8_0 17.2 GB
GE
Models Google Gemma 3 4b It
Gemma · MaziyarPanahi
Params3.88B
Context128K
Q4_K_M2.5 GB
DE
DeepSeek R1 0528 Qwen3 8B
DeepSeek · lmstudio-community
Params8.19B
Context128K
Best fitQ8_0 10.4 GB
KE
Kev 4B
Kev · ggml-org
Params4.2B
Context256K
Best fitBF16 10.0 GB
QW
Qwen3.5 27B
Qwen · bartowski
Params27.3B
Context256K
Best fitQ8_0 31.8 GB
QW
Qwen3.8 27B ABLITERATED BF16
Qwen · Blackfrost-AI
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
LL
Meta-Llama-3-70B-Instruct-abliterated-v3.5
Llama · legraphista
Params70.6B
Context8K
Best fitQ4_K 45.7 GB
NE
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
Nemotron · ggml-org
Params1.66B
Context1024K
Best fitBF16 8.7 GB
WH
WhiteRabbitNeo-33B-v1.5
Whiterabbitneo · manuelgutierrez
Params33.3B
Context16K
Best fitQ8_0 38.0 GB
QW
Qwen3.8 9B Heretic Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
QW
Qwen3.5-122B-A10B
Qwen · unsloth
Params122B
Context256K
Best fitIQ3_S 47.9 GB
QW
Qwen Image 2.1 PE I2I
Qwen · prithivMLmods
Params8.95B
Context256K
Best fitBF16 19.5 GB
GE
Gemma-3-1B-It
Gemma · unsloth
Params1B
Context32K
Best fitBF16 2.7 GB
UN
Underdog Saluki 27B 1.0 MTP
Underdog · Kujira
Params27.3B
Context256K
Smallest8.3 GB
ST
stable diffusion v1 5
Stable · second-state
Params1.07B
Context—
Best fitF32 5.3 GB
QW
Qwen3.8 27B TWIN TURBO Fable Cold Fusion 709 L Uncensored NM DAU NEO MTP
Qwen · DavidAU
Params27B
Context256K
Best fitQ8_0 32.9 GB
AN
anthracite org magnum 12b v2
Anthracite · RichardErkhov
Params12.2B
Context—
Best fitIQ3_M 6.9 GB
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · bartowski
Params15.7B
Context160K
Best fitQ8_0 19.9 GB
QW
Qwen3.6 35B A3B Uncensored Heretic Native MTP Preserved
Qwen · SC117
Params447M
Context256K
Smallest14.3 GB
NE
Nemotron 3.5 Bolt E4B
Nemotron · nvidia
Params7.52B
Context64K
Best fitQ4_K_M 8.1 GB
TE
Ternary Bonsai 2 27B Uncensored Heretic v2
Ternary · OS-Software
Params27B
Context256K
Smallest5.9 GB
MI
models--mistralai--Mistral-7B-Instruct-v0.3
Mistral · MaziyarPanahi
Params7.25B
Context32K
Q4_K_M4.4 GB
JI
Jina Embeddings v5 Text Nano Retrieval
Jina · jinaai
Params212M
Context8K
Best fitF16 1.2 GB
MI
Ministral 3 3B Instruct 2512
Mistral · mistralai
Params3.43B
Context256K
Best fitBF16 8.2 GB
CO
C4Ai Command R7B 12 2024
Command R · bartowski
Params8B
Context8K
Best fitF32 33.7 GB
QW
Qwen3.6 27B
Qwen · bartowski
Params27.3B
Context256K
Best fitQ8_0 31.8 GB
MI
models--v2ray--Mixtral-8x22B-v0.1
Mistral · MaziyarPanahi
Params141B
Context64K
Best fitIQ1_M 35.1 GB
QW
Qween3 4B thinking finetune
Qween · pramodlohra
Params4B
Context256K
Best fitQ4_K_M 4.2 GB
QW
Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated
Qwen · huihui-ai
Params35.5B
Context256K
Best fitQ8_0 39.0 GB