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
Qwen · lmstudio-community
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
GGUF
JA
Jan nano
Jan · Menlo
Params4B
Context40K
Best fitQ8_0 6.0 GB
GGUF
QW
Dongfangshuo Qwen3.8 27B NSFW
Qwen · dongfangshuo
Params27.3B
Context256K
Best fitQ4_K_M 19.5 GB
Vision
OZ
lyrics room final refiner ozan v1
Ozan · rambrogi
Params12.2B
Context128K
Best fitQ8_0 14.9 GB
GGUF
WI
Wicked Stuff 26B A4B v3.0 Final
Wicked · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
ReasoningTool use
XY
Xyntetik Kvist 14B
Xyntetik · mradermacher
Params14.4B
Context128K
Best fitQ6_K 15.3 GB
Tool use
LU
Lumimaid v0.2 12B
Lumimaid · NeverSleep
Params12.2B
Context1000K
Best fitQ8_0 14.9 GB
GGUF
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Best fitQ6_K 5.9 GB
GGUF
HU
Hunyuan 0.5B Instruct
Hunyuan · bartowski
Params539M
Context256K
Best fitBF16 2.4 GB
GGUF
GR
Granite 3.1 2b Instruct
Granite · bartowski
Params2.53B
Context128K
Best fitF16 6.2 GB
GGUF
QW
Qwen3-4B-abliterated
Qwen · Mungert
Params4B
Context40K
Best fitBF16 9.8 GB
GGUF
YI
dolphin-2.9.3-Yi-1.5-34B-32k
Yi · mradermacher
Params34.4B
Context32K
Best fitQ6_K 30.7 GB
CodingTool use
QW
Qwen2.5 VL 32B Instruct
Qwen · lmstudio-community
Params32.8B
Context125K
Best fitQ8_0 37.5 GB
Vision
OM
Omega Arsenal 12B
Omega · mradermacher
Params11.9B
Context256K
Best fitQ6_K 23.2 GB
ReasoningTool use
PY
Pythia 410m
Pythia · mradermacher
Params405M
Context2K
Best fitQ4_0 1.6 GB
GGUF
LL
Llama 7B rollercoaster v2 i1
Llama · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
GGUF
MI
nondzu_mistral-7b-instruct-v0.2-code-ft
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
Coding
GE
Vikhr-Gemma-2B-instruct
Gemma · Vikhrmodels
Params2.61B
Context8K
Best fitF32 11.8 GB
GGUF
FI
SUFE AIFLM Lab Fin R1
Fin · bartowski
Params7.6B
Context32K
Best fitBF16 16.2 GB
Reasoning
QW
Qwen3.5 35B A3B Claude Distilled APEX
Qwen · mudler
Params34.7B
Context256K
Smallest14.3 GB
Reasoning
AR
Artemis 31B v1.2
Artemis · Abiray
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
RoleplayVision
QW
Qwen3 Uncensored TextEncoders Klein Z Image Anima
Qwen · LuffyTheFox
Params596M
Context40K
Best fitQ8_0 10.1 GB
Coding
TE
Terminal RSI 27B
Terminal · bartowski
Params27.3B
Context256K
Best fitQ8_0 31.8 GB
CodingReasoningTool use
QW
Qwen3.6 27B A3B CoderX
Qwen · ManniX-ITA
Params26.2B
Context256K
Best fitQ8_0 29.1 GB
Coding
LI
LightOnOCR 3 0.8B
Lightonocr · NANI-Nithin
Params752M
Context256K
Best fitBF16 2.4 GB
GGUF
PH
phi-4-mini-instruct
Phi · Mungert
Params3.84B
Context128K
Best fitBF16 9.3 GB
CodingReasoning
LU
Lunar Huntress 0.1
Lunar · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
ReasoningRoleplayTool use
QW
Replete LLM V2.5 Qwen 14b
Qwen · bartowski
Params14.8B
Context32K
Best fitF16 31.7 GB
GGUF
QW
Qwen3.5 9B The Bradbury F451 Pro Writer Uncensored Heretic
Qwen · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
CodingRoleplayVision
QW
Qwen3.5 9B C3SM SDM Agentic Coder
Qwen · OliviaRossi
Params8.95B
Context256K
Best fitQ5_K_M 8.0 GB
CodingTool use

Other memory sizes

Keep browsing