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
IN
Ingot XI 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
ReasoningTool use
GL
GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive
GLM · HauhauCS
Params30B
Context198K
Best fitQ8_0 33.2 GB
GGUF
LL
LIama 3.2 test
Llama · bhanuripranathi
Params3.21B
Context128K
Best fitQ4_K_M 3.5 GB
GGUF
QW
Qwen3.8 Flash Next
Qwen · AesSedai
Params180B
Context256K
Q4_K_M116.1 GB
Vision
AR
AREX Turbo
Arex · bartowski
Params4.2B
Context256K
Best fitBF16 10.0 GB
ReasoningTool useVision
MA
magnum v4 12b
Magnum · anthracite-org
Params12.2B
Context1000K
Best fitQ8_0 14.9 GB
GGUF
KI
Kimi VL A3B Thinking 2506
Kimi · ggml-org
Params16B
Context128K
Best fitBF16 32.9 GB
ReasoningVision
WI
Wicked Stuff 26B A4B v2.0 Final
Wicked · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
ReasoningTool use
BO
Borealis Open 27b
Borealis · mradermacher
Params27B
Context128K
Best fitQ6_K 26.8 GB
GGUF
GL
GLM 4 32B 0414
GLM · bartowski
Params32.6B
Context32K
Best fitQ8_0 35.6 GB
GGUF
QW
Qwen3.8 27B Uncensored
Qwen · shsunshining
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
Vision
TW
Twisted Cyclone 31B
Twisted · mradermacher
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
RoleplayVision
QW
Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
Reasoning
LF
LFM2.5-8B-A1B-Uncensored-Gaston
Lfm · gaston-parravicini
Params8.47B
Context125K
Best fitQ8_0 11.1 GB
Reasoning
OM
Omega Arsenal 26B A4B Final
Omega · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
ReasoningTool use
QW
Qwen2.5 Coder 1.5B
Qwen · ggml-org
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
Coding
IN
Ingot V 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
ReasoningTool use
OR
RegesCore 1.0 35
Ornith · iBossonline
Params34.7B
Context256K
Best fitQ8_K_XL 39.4 GB
ReasoningVision
HE
Hemmingway 1 Heretic MTP V3 Vision
Hemmingway · brainnxdomain
Params27B
Context256K
Best fitQ8_0 31.2 GB
ReasoningVision
MI
MegaBeam Mistral 7B 512k
Mistral · bartowski
Params7.24B
Context512K
Best fitF16 16.1 GB
GGUF
QW
Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled APEX MTP
Qwen · mudler
Params35.5B
Context256K
Smallest11.7 GB
Reasoning
HY
Hy MT2 1.8B 1.25Bit
tencent
Params1.79B
Context256K
Smallest0.5 GB
GGUF
JE
Jebadiah 9b v2
Jebadiah · bartowski
Params9.2B
Context256K
Best fitBF16 20.0 GB
Vision
TI
TinyLlama 1.1B Chat v0.6
Tinyllama · TinyLlama
Params1.1B
Context2K
Best fitQ4_0 1.3 GB
Coding
MI
ehartford_dolphin-2.1-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
BA
Bathory X 26B A4B 0.1
Bathory · mradermacher
Params26B
Context256K
Best fitQ6_K 31.8 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · mradermacher
Params8B
Context128K
Best fitF16 17.6 GB
Reasoning
QW
qwen2.5 coder 32b bitnet 1.58b
Qwen · tzervas
Params32.8B
Context32K
Smallest11.2 GB
Coding
QW
Huihui Qwen3 Next 80B A3B Instruct Abliterated
Qwen · mradermacher
Params80B
Context256K
Best fitQ4_K_S 46.8 GB
GGUF
GE
Gemma 3 270m Qat Q4_0 Unquantized
Gemma · ggml-org
Params268M
Context32K
Best fitQ4_0 0.9 GB
GGUF

Other memory sizes

Keep browsing