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
Qwen3 0.6b Abliterated
Qwen · mradermacher
Params596M
Context40K
Best fitQ5_K_S 1.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B Uncensored
DeepSeek · mradermacher
Params32.8B
Context128K
Best fitQ8_0 37.5 GB
Reasoning
QW
Whittle Qwen 3.8 35B A3B
Qwen · logic65
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
CodingReasoning
GL
Models Zai Org GLM 4.6V Flash
GLM · MaziyarPanahi
Params9.4B
Context128K
Q4_K_M6.2 GB
GGUF
AG
Agents A1
Agents · InternScience
Params34.7B
Context256K
Best fitQ4_K_M 22.3 GB
Vision
MI
MiniCPM-V-4.7-35B-A3B
MiniCPM · AtomicChat
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
ReasoningTool useVision
GP
Models ArliAI Gpt Oss 20b Derestricted
gpt-oss · MaziyarPanahi
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
MI
mistralai_Ministral 3 3B Instruct 2512 BF16
Mistral · lmstudio-community
Params3.43B
Context256K
Best fitQ8_0 5.0 GB
Vision
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
ReasoningTool use
MU
Muse Glimmer 30B
Muse · bartowski
Params27.9B
Context128K
Best fitQ8_0 30.5 GB
Vision
GE
Gemma-4-12B-OBLITERATED-v2
Gemma · OBLITERATUS
Params11.9B
Context128K
Best fitBF16 37.2 GB
Vision
GL
cerebras/GLM-4.7-Flash-REAP-23B-A3B
GLM · unsloth
Params23B
Context198K
Best fitBF16 47.3 GB
GGUF
OR
Ornith 1.5 9B Heretic v2
Ornith · Thunder13240
Params8.95B
Context256K
Best fitBF16 19.5 GB
ReasoningVision
MI
mistralai_mixtral-8x7b-instruct-v0.1
Mistral · TheBloke
Params46.7B
Context32K
Best fitQ6_K 40.0 GB
GGUF
JI
JiRackUltra 1b
Jirackultra · CMSManhattan
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
NA
Nanbeige4.3 33B UNCENSORED
Nanbeige · dealignai
Params33.1B
Context512K
Best fitQ6_K 29.4 GB
ReasoningTool use
MI
Devstral Small 2 24B Instruct 2512
Mistral · bartowski
Params23.6B
Context384K
Best fitQ8_0 26.9 GB
Coding
QW
Qwen3 VL 2B Instruct
Qwen · ggml-org
Params1.72B
Context256K
Best fitQ8_0 3.3 GB
Vision
LL
codellama_codellama-7b-instruct-hf
Llama · TheBloke
Params6.74B
Context16K
Best fitQ8_0 12.0 GB
Coding
GP
Huihui Gpt Oss 20b Mxfp4 Abliterated v2
gpt-oss · huihui-ai
Params20.9B
Context128K
Best fitMXFP4 14.7 GB
GGUF
MI
MistralRP Noromaid NSFW Mistral 7B
Mistral · Ttimofeyka
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
QW
Qwen3.8 27B Uncensored
Qwen · BnhHo
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
Vision
QW
Qwen3.8-27B-DFlash2
Qwen · incoai
Params1.92B
Context256K
Best fitBF16 4.5 GB
GGUF
QW
Huihui Qwen3 VL 8B Instruct Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Best fitF16 18.1 GB
Vision
BG
bge m3 Q8 0
BGE · ggml-org
Params567M
Context8K
Best fitQ8_0 1.9 GB
Embedding
NE
NVIDIA Nemotron Nano 9B v2
Nemotron · bartowski
Params8.89B
Context1024K
Best fitBF16 27.7 GB
GGUF
QW
Qwen3-Vl-30B-A3B-Instruct
Qwen · unsloth
Params30.5B
Context256K
Best fitQ8_K_XL 37.3 GB
Vision
QW
Huihui Qwen3.8 27B Coder390 EfficientThink Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
CodingVision
GE
gemma 7b it
Gemma · google
Params8.54B
Context—
Smallest34.2 GB
GGUF
GE
supergemma4 26b uncensored gguf v2
Gemma · Jiunsong
Params25.2B
Context256K
Best fitQ4_K_M 25.3 GB
Tool use

Other memory sizes

Keep browsing