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.
SW
Swish 26B A4B
Swish · ReadyArt
Params25.2B
Context256K
Best fitQ8_0 36.1 GB
RU
RusMind 4.6.5 Momentum
Rusmind · DICPlay
Params4.65B
Context128K
Best fitBF16 10.4 GB
QW
Qwen2.5 Coder 14B Instruct
Qwen · unsloth
Params14.8B
Context32K
Best fitF16 31.7 GB
MI
migtissera_synthia-moe-v3-mixtral-8x7b
Mistral · TheBloke
Params46.7B
Context32K
Best fitQ6_K 40.0 GB
QW
hpc assistant qwen3 4b
Qwen · VaibhavKKM
Params4.02B
Context256K
Best fitQ8_0 6.0 GB
QW
Qwen3 4B 2507 abliterated
Qwen · prithivMLmods
Params4B
Context256K
Best fitF32 17.8 GB
MI
colgrep-agent-2B
MiniCPM · lightonai
Params2.52B
Context128K
Best fitBF16 5.9 GB
QW
HIDra-30B-A3B
Qwen · SAPSAN-SKLEP
Params30.5B
Context256K
Best fitQ8_0 33.8 GB
QW
Huihui Qwen3.5 0.8B Abliterated
Qwen · mradermacher
Params752M
Context256K
Best fitF16 2.4 GB
CO
C4Ai Command R Plus 08 2024
Command R · legraphista
Params104B
Context128K
Best fitIQ3_XS 46.2 GB
SI
Signal 3.8 27B Terse Coder
Signal · mradermacher
Params27.3B
Context256K
Best fitQ6_K 25.1 GB
MI
Devstral Small 2 24B Instruct 2512
Mistral · ggml-org
Params23.6B
Context384K
Best fitQ8_0 26.9 GB
MI
Ministral 3 8B Reasoning UNCENSORED Heretic
Mistral · mradermacher
Params8.49B
Context256K
Best fitQ6_K 8.6 GB
GR
Granite 20b Code Instruct R1.1
Granite · RichardErkhov
Params20B
Context8K
Best fitQ8_0 22.2 GB
RN
EssentialAI_rnj 1 Instruct
Rnj · lmstudio-community
Params8.3B
Context32K
Best fitQ8_0 10.4 GB
BA
bagel dpo 34b v0.5 i1
Bagel · mradermacher
Params34.4B
Context195K
Best fitQ6_K 31.3 GB
GE
Gemma 4 Dark Thoughts 31B
Gemma · bartowski
Params30.7B
Context256K
Best fitIQ3_M 47.8 GB
QW
Qwen3 VL Embedding 2B
Qwen · mradermacher
Params1.72B
Context256K
Best fitF16 4.9 GB
QW
Qwen3.8-27B
Qwen · loscrossos
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NM DAU NVFP4
Qwen · esatapedico
Params27.3B
Context256K
Smallest15.2 GB
FA
Falcon 11B
Falcon · mradermacher
Params11.1B
Context2K
Best fitQ6_K 11.7 GB
QW
Qwen3.5 35B A3B ultra uncensored heretic
Qwen · llmfan46
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
PH
Phi 3 Medium 4k Instruct
Phi · bartowski
Params14B
Context4K
Best fitQ8_0 17.0 GB
QW
Qwen Qwen3 VL 8B Instruct Heretic
Qwen · ThalisAI
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
NE
NVIDIA-Nemotron-3.5-Bolt-E4B
Nemotron · AtomicChat
Params7.52B
Context64K
Best fitQ8_0 9.9 GB
PY
Pygmalion 2 7B
Pygmalion · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
OR
Ornith-1.5-35B
Ornith · peculiar-ragdoll
Params34.7B
Context256K
Best fitQ8_K_XL 39.6 GB
GE
Gemma 3 4B VL It Gemini Pro Heretic Uncensored Thinking
Gemma · mradermacher
Params3.88B
Context128K
Best fitF16 9.4 GB
QW
Qwen3 VL 4B Instruct Uncensored Abliterated
Qwen · mradermacher
Params4.02B
Context256K
Best fitF16 9.8 GB
GE
Gemma 4 31B StyleTune Heretic Ara
Gemma · mradermacher
Params32.1B
Context256K
Best fitIQ3_M 47.7 GB