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
Qwen3.6 35B A3B 2Bit GSQ hybrid
Qwen · chtisgit
Params34.7B
Context256K
Smallest12.2 GB
Vision
GE
Gemma 4 E2B it Artemis
Gemma · turintech
Params4.63B
Context128K
Best fitQ3_K_L 2.9 GB
ReasoningTool useVision
NE
Huihui NeoHorse 1 4B Abliterated MTP
Neohorse · huihui-ai
Params4.33B
Context256K
Best fitF16 10.3 GB
ReasoningTool useVision
GL
Glm-4-32B-0414
GLM · unsloth
Params32.6B
Context32K
Best fitQ8_K_XL 40.5 GB
GGUF
IN
Ingot I 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
ReasoningTool use
QW
Qwen3.8 9B Heretic Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
GGUF
TI
Tifa DeepsexV3 14b GGUF Q6
Tifa · ValueFX9507
Params14.8B
Context32K
Smallest12.1 GB
Roleplay
QW
Qwen3.6 VL REAP 26B A3B
Qwen · keithnull
Params26.6B
Context256K
Best fitQ4_K_M 17.4 GB
ReasoningTool useVision
GR
Granite 4.0 H Tiny
Granite · ibm-granite
Params6.94B
Context1024K
Best fitBF16 16.4 GB
GGUF
GE
gemma 4 31B it
Gemma · AtomicChat
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
ReasoningTool useVision
BI
Bielik-11B-v3.0-Instruct
Bielik · speakleash
Params11.2B
Context32K
Best fitBF16 24.5 GB
GGUF
OR
Ornith 1.5 35B A3B
Ornith · SC117
Params447M
Context256K
Smallest14.4 GB
ReasoningVision
CL
Diffuspace/Clover-35B-A3B-Preview
Clover · maternion
Params34.7B
Context128K
Best fitQ8_0 38.1 GB
Coding
QW
Qwen2.5 Coder 14B
Qwen · bartowski
Params14.8B
Context32K
Best fitF16 31.7 GB
Coding
GE
Gemma 4 31B Heretic
Gemma · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
GGUF
PH
Phi 3 mini 4k instruct
Phi · bartowski
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
PH
Phi-4-Reasoning-Plus
Phi · unsloth
Params14.7B
Context32K
Best fitBF16 31.5 GB
CodingReasoning
LL
WizardLM 1.0 Uncensored Llama2 13B
Llama · TheBloke
Params13B
Context4K
Best fitQ8_0 21.0 GB
GGUF
OR
Orpheus-3B-0.1-Ft
Orpheus · unsloth
Params3.3B
Context128K
Best fitF16 8.1 GB
GGUF
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · lmstudio-community
Params32.8B
Context128K
Best fitQ8_0 37.5 GB
Reasoning
SP
speechless zephyr code functionary 7b
Speechless · uukuguy
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
CodingTool use
QW
Qwen3.8 27B Heretic JP Roleplay NSFW
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
Roleplay
QW
JoyFox-Qwen3.6-35B-A3B-RP-Aggressive
Qwen · joyfox
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
RoleplayVision
AG
Agri 31b v1
Agri · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507
Qwen · lmstudio-community
Params4B
Context256K
Best fitQ8_0 6.0 GB
Reasoning
QW
Qwen3Vl 8b Thinking
Qwen · Qwen
Params8.19B
Context256K
Best fitF16 18.1 GB
ReasoningVision
MU
music flamingo
Music · henry1477
Params7.6B
Context32K
Best fitBF16 16.2 GB
ReasoningVision
TE
Ternary Bonsai 2 27B Heretic Satellite
Ternary · HybridRMD
Params27B
Context256K
Best fitQ8_0 31.2 GB
GGUF
JI
JiRackDeltaNet 27b
Jirackdeltanet · CMSManhattan
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
ReasoningTool use
GE
gemma 4 31B it scotoma 2
Gemma · ReadyArt
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
Vision

Other memory sizes

Keep browsing