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 Coder 32b Instruct Heretic Sft
Qwen · mradermacher
Params32.8B
Context32K
Best fitQ6_K 29.5 GB
Coding
QW
Huihui Qwen3 4B Instruct 2507 Abliterated
Qwen · mradermacher
Params4B
Context256K
Best fitF16 9.8 GB
GGUF
GE
Gemma 4 12B It Abliterated Uncensored
Gemma · mradermacher
Params11.9B
Context128K
Best fitQ8_0 26.1 GB
ReasoningTool useVision
GE
Huihui gemma 4 E4B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params7.46B
Context128K
Best fitQ4_0 15.6 GB
Vision
FL
flux2 klein 9b uncensored text encoder
Flux · ponpoke
Params8.19B
Context—
Best fitF16 18.9 GB
Coding
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · huihui-ai
Params3.09B
Context125K
Best fitF16 7.0 GB
Vision
QW
Qwen3 0.6B Heretic Heresy Edition
Qwen · mradermacher
Params596M
Context40K
Best fitF16 2.6 GB
ReasoningTool use
JA
Jais-3-32B
Jais · mradermacher
Params34.8B
Context512K
Best fitQ8_0 39.6 GB
ReasoningTool use
QW
Qwen3.5 4B Uncensored LocalAI
Qwen · weareapexcreators
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
Vision
QW
Qwen3.6 35B A3b pruned v2
Qwen · gatilin
Params26.6B
Context256K
Smallest16.3 GB
GGUF
QW
Huihui Qwen3 VL 30B A3B Instruct Abliterated
Qwen · noctrex
Params30.5B
Context256K
Best fitQ8_0 33.8 GB
Vision
XY
XYZ Aquila Mini
Xyz · bartowski
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
Vision
HU
Hunyuan MT 7B
Hunyuan · mradermacher
Params7.5B
Context256K
Best fitF16 16.6 GB
GGUF
LF
LFM3 1.7B
Lfm · LiquidAI
Params1.73B
Context256K
Best fitBF16 5.6 GB
ReasoningTool use
LL
Llama 3.3 70B Instruct
Llama · lmstudio-community
Params70.6B
Context128K
Best fitQ4_K_M 45.7 GB
GGUF
AR
BAAI AREX 2
Arex · bartowski
Params27B
Context256K
Best fitQ8_0 31.3 GB
ReasoningTool useVision
QW
Qwen3.8 Whittle MoE 27B A17.8B
Qwen · logic65
Params26.9B
Context256K
Best fitQ8_0 31.3 GB
Vision
QW
Qwen3.8 27B Heretic JP Roleplay NSFW
Qwen · mradermacher
Params27B
Context256K
Best fitQ8_0 31.2 GB
RoleplayVision
NE
NVIDIA Nemotron Labs Dory1.0 4B
Nemotron · nvidia
Params3.98B
Context256K
Best fitQ5_K_M 6.6 GB
ReasoningTool use
BA
BarryFutureman NeuralTurdusVariant1 7B
Barryfutureman · RichardErkhov
Params7B
Context—
Best fitIQ3_S 4.1 GB
GGUF
QW
Qwen3.6 35B A3B Uncensored Heretic
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
GGUF
OR
Ornith-1.5-122B
Ornith · AtomicChat
Params125B
Context256K
Best fitIQ2_S 44.1 GB
ReasoningTool useVision
MI
MiniCPM V 4_6
MiniCPM · openbmb
Params752M
Context256K
Best fitF16 2.4 GB
Vision
LF
LFM2.5 2.6B UNCENSORED ABLITERATED PHILADELPHIA CLASS
Lfm · PhillyLabs
Params2.7B
Context125K
Best fitBF16 7.9 GB
Reasoning
GE
Gemma-3-4B-It-Qat
Gemma · unsloth
Params3.88B
Context128K
Best fitBF16 9.4 GB
Vision
QW
Qwen3.5-0.8B
Qwen · weareapexcreators
Params773M
Context256K
Best fitQ4_K_M 1.5 GB
Vision
QW
Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled
Qwen · hesamation
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
Reasoning
QW
Qwen2 VL 2B Instruct
Qwen · bartowski
Params1.54B
Context32K
Best fitF16 3.8 GB
Vision
RO
L3.2 Rogue Creative Instruct Uncensored Abliterated 7B
Rogue · DavidAU
Params7.53B
Context128K
Best fitQ8_0 10.8 GB
Roleplay
QW
Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled APEX
Qwen · mudler
Params34.7B
Context256K
Smallest11.6 GB
ReasoningVision

Other memory sizes

Keep browsing