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
QW
Qwen2.5 1.5B Instruct uncensored
Qwen · mradermacher
Params1.78B
Context32K
Best fitF16 4.3 GB
GGUF
LL
jarradh_llama2_70b_chat_uncensored
Llama · TheBloke
Params69B
Context2K
Best fitQ4_K_M 44.6 GB
GGUF
MI
teknium_openhermes-2.5-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
Tool use
MI
Devstral-Small-2507
Mistral · unsloth
Params23.6B
Context128K
Best fitQ8_K_XL 30.8 GB
CodingVision
CO
Computer 10
Computer · bartowski
Params70.6B
Context128K
Best fitQ4_1 48.0 GB
GGUF
QW
Qwen3 Next 80B A3B Thinking
Qwen · bartowski
Params80B
Context256K
Best fitQ4_0 47.4 GB
Reasoning
VE
Veloxy Flash 15B i1
Veloxy · zveloxy
Params8.95B
Context512K
Best fitQ8_0 11.1 GB
Reasoning
GE
Gemma 4 E4B It OBLITERATED v3.1
Gemma · Aimeeluvssya
Params7.52B
Context128K
Best fitQ8_0 9.9 GB
ReasoningTool useVision
QW
Qwen3.8 27B OBLITERATED
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
Vision
QW
Qwen3.5 9B Uncensored
Qwen · LEONW24
Params9.65B
Context256K
Best fitQ4_K_M 11.5 GB
GGUF
LL
Dolphin3.0 Llama3.1 8B Abliterated
Llama · mradermacher
Params8B
Context128K
Best fitF16 17.6 GB
GGUF
ME
Mellum2.1 12B A2.5B Thinking
Mellum · bartowski
Params12.1B
Context128K
Best fitBF16 25.3 GB
Reasoning
D1
d1 2B
LiquidAI
Params1.73B
Context125K
Best fitBF16 5.6 GB
ReasoningTool useVision
PH
Phi-4-Mini-Reasoning
Phi · unsloth
Params3.84B
Context128K
Best fitBF16 9.3 GB
CodingReasoning
MI
MiniCPM V 4.7 1B LocalAI
MiniCPM · weareapexcreators
Params1.01B
Context256K
Best fitQ8_0 2.0 GB
Vision
MI
mistralai_mixtral-8x7b-v0.1
Mistral · TheBloke
Params46.7B
Context32K
Best fitQ6_K 40.0 GB
GGUF
NA
vllm-d3-nano
Nano · ggml-org
Params2.4B
Context256K
Best fitBF16 5.7 GB
Vision
TO
Torchcast Decision 12b
Torchcast · mradermacher
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
Vision
ME
G4 MeroMero v2 31B Heretic
Meromero · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
GGUF
QW
Qwen2.5 VL 7B NSFW Caption V3
Qwen · bartowski
Params7.62B
Context125K
Best fitBF16 16.2 GB
Vision
PH
Phi 3 mini 4k instruct GGUF Imatrix smashed
Phi · PrunaAI
Params3.82B
Context4K
Best fitQ8_0 7.8 GB
GGUF
NE
Nemotron 3 Nano Omni 30B A3B Reasoning APEX
Nemotron · mudler
Params31.6B
Context1024K
Smallest18.0 GB
ReasoningVision
LU
LunaraHome 26B A4B
Lunarahome · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
Tool use
QW
Qwen2.5 7B Instruct Abliterated
Qwen · richardyoung
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
GGUF
GE
Gemma 4 Novelist Eclipse 31B
Gemma · mradermacher
Params32.1B
Context256K
Best fitIQ3_M 47.7 GB
Roleplay
OR
Ornith 1.5 122B
Ornith · bartowski
Params125B
Context256K
Best fitIQ2_M 47.7 GB
Vision
LL
Lexi-Llama-3-8B-Uncensored
Llama · bartowski
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
QW
Qwopus3.5 9B Coder Templatefix Hf
Qwopus · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
CodingReasoningTool use
ST
StartLux Decision v1 4B Q8 0
Startlux · startlux-models
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
GGUF
MI
Dolphin3.0 R1 Mistral 24B
Mistral · bartowski
Params23.6B
Context32K
Best fitQ8_0 26.9 GB
CodingReasoningTool use

Other memory sizes

Keep browsing