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
LL
Colossal LLaMA 2 7b Base
Llama · mradermacher
Params7.04B
Context4K
Best fitQ6_K 10.6 GB
GGUF
MI
mathstral-7B-v0.1
Mistral · bartowski
Params7.25B
Context32K
Best fitF32 30.6 GB
GGUF
AN
Anubis Mini 8B v1
Anubis · bartowski
Params8B
Context128K
Best fitBF16 17.6 GB
GGUF
AI
Airochronos L2 13B
Airochronos · TheBloke
Params13B
Context4K
Best fitQ8_0 21.0 GB
GGUF
QW
QwQ 32B Abliterated
Qwen · bartowski
Params32.8B
Context128K
Best fitQ8_0 37.5 GB
Reasoning
MI
Mixtral-instruct-56B
Mistral · mradermacher
Params46.7B
Context32K
Best fitQ6_K 40.0 GB
Vision
LL
Llama 3.1 70B Instruct
Llama · mradermacher
Params70.6B
Context128K
Best fitQ4_K_M 45.7 GB
GGUF
NO
nomic-embed-text-v1.5
Nomic · second-state
Params137M
Context2K
Best fitF16 1.1 GB
Embedding
GE
Gemma-3-270M-It-Qat
Gemma · unsloth
Params268M
Context32K
Best fitF16 1.2 GB
GGUF
LL
ShiningValiantXS 1.1
Llama · TheBloke
Params13B
Context4K
Best fitQ8_0 21.0 GB
GGUF
JI
Jina Embeddings v5 Text Nano Classification
Jina · jinaai
Params212M
Context8K
Best fitF16 1.2 GB
CodingEmbedding
QW
calme-2.2-qwen2-72b
Qwen · MaziyarPanahi
Params72.7B
Context32K
Best fitQ4_K_S 47.1 GB
GGUF
NO
Novel Humanize 4b
Novel · bartowski
Params4.02B
Context40K
Best fitBF16 9.8 GB
ReasoningTool use
NI
Ninja-v1-NSFW-RP
Ninja · mradermacher
Params7.24B
Context4K
Best fitQ6_K 7.5 GB
Roleplay
NE
NVIDIA Nemotron 3.5 Super VL 120B A12B heretic ara i1
Nemotron · spiritfather
Params121B
Context1024K
Best fitBF16 20.4 GB
Vision
LL
dolphin-2.9.1-llama-3-8b
Llama · legraphista
Params8B
Context8K
Best fitBF16 17.6 GB
CodingTool use
LL
phind_phind-codellama-34b-v1
Llama · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
Coding
HU
HuatuoGPT O1 7B
Huatuogpt · mradermacher
Params7.62B
Context32K
Best fitF16 16.2 GB
Reasoning
HU
Huihui LFM2.5 8B A1B Abliterated
Huihui · mradermacher
Params8.47B
Context125K
Best fitQ6_K 9.1 GB
GGUF
LF
LFM2.5-24B-A2B
Lfm · ngquocvinh
Params24B
Context128K
Best fitQ8_0 28.7 GB
GGUF
QW
Darrellbest Qwen Image 2.1 PE T2I Heretic
Qwen · darrellbest
Params8.95B
Context256K
Best fitBF16 19.5 GB
GGUF
LL
georgesung_llama2_7b_chat_uncensored
Llama · TheBloke
Params6.74B
Context2K
Best fitQ8_0 12.0 GB
GGUF
TO
tolkio models
Tolkio · datacrunch
Params1.94B
Context256K
Smallest0.6 GB
ReasoningTool use
NO
Nora0.1 1.7B
Nora · mradermacher
Params1.72B
Context40K
Best fitQ6_K 2.9 GB
ReasoningRoleplayTool use
GE
Tiger Gemma 12B v3
Gemma · bartowski
Params12.8B
Context128K
Best fitBF16 29.3 GB
Vision
JI
Jina Embeddings v5 Text Small Clustering
Jina · jinaai
Params596M
Context32K
Best fitF16 2.6 GB
Embedding
LF
LFM3 1.7B Heretic Abliterated
Lfm · Vortecks
Params1.73B
Context256K
Best fitF32 9.0 GB
ReasoningTool use
NE
nexusflow_nexusraven-v2-13b
Nexusraven · TheBloke
Params13B
Context16K
Best fitQ8_0 21.0 GB
GGUF
NE
NeuralDaredevil 8B abliterated
Neuraldaredevil · QuantFactory
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
WH
whisper large v3 turbo
Whisper · oxide-lab
Params809M
Context—
Best fitQ8_0 1.5 GB
GGUF

Other memory sizes

Keep browsing