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
PH
Phi 4 Mini Reasoning
Phi · lmstudio-community
Params3.84B
Context128K
Best fitQ8_0 5.7 GB
CodingReasoning
PU
PuddleJumper 13B
Puddlejumper · TheBloke
Params13B
Context4K
Best fitQ8_0 21.0 GB
GGUF
ST
berkeley-nest_starling-lm-7b-alpha
Starling · TheBloke
Params7.24B
Context8K
Best fitQ8_0 9.3 GB
GGUF
QW
Qwopus3.6 27B v2
Qwen · Jackrong
Params461M
Context256K
Best fitQ8_0 31.7 GB
CodingReasoningTool use
QW
Qwen3 14B ARPO DeepSearch
Qwen · mradermacher
Params14.8B
Context40K
Best fitQ6_K 14.0 GB
Tool use
JE
JEV 9B
Jev · prithivMLmods
Params8.95B
Context256K
Best fitBF16 19.5 GB
GGUF
QW
Qwen3.8-27B-DFlash2-ternary-bonsai2-r3
Qwen · naklitechie
Params1.92B
Context256K
Best fitQ4_K_M 1.8 GB
GGUF
QW
Qwen3.5 4B Heretic
Qwen · darrellbest
Params4.33B
Context256K
Best fitBF16 10.3 GB
Vision
MY
Mythos v2 9b
Mythos · fableforge-ai
Params9.2B
Context256K
Best fitF16 20.0 GB
Tool use
HO
Holo 3.1 4B
Holo · mradermacher
Params4.84B
Context256K
Best fitF16 11.3 GB
ReasoningTool useVision
NE
Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive
Nemotron · HauhauCS
Params3.97B
Context1024K
Best fitQ8_K 12.2 GB
GGUF
MI
devstral-small-2507
Mistral · mistralai
Params23.6B
Context128K
Best fitQ8_0 26.9 GB
Coding
TO
tokyotech llm Swallow MS 7b instruct v0.1
Tokyotech · mmnga
Params7.33B
Context4K
Best fitQ8_0 9.4 GB
GGUF
LL
codellama_codellama-34b-hf
Llama · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
Coding
QW
qwen2-7b-instruct
Qwen · Qwen
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
GE
Gemma4 12B IT Abliterated
Gemma · DuoNeural
Params11.9B
Context128K
Best fitQ8_0 26.1 GB
Vision
XO
Xor 26B A4B
Xor · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
GGUF
QW
Qwen 35B A3B SignOfFour Coder
Qwen · pragmaticcs
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
CodingReasoningTool use
PR
Promethean Dawn 26B A4B
Promethean · mradermacher
Params26B
Context256K
Best fitQ6_K 31.8 GB
Roleplay
QW
Qwen3.5 9B Cold Fusion GAIN v1.0 Uncensored Heretic NEO MAX Imatrix
Qwen · DavidAU
Params8.95B
Context256K
Best fitQ8_0 12.3 GB
CodingReasoningRoleplay
QW
Qwen3.5 0.8B GGUF uncensored opus distill
Qwen · amkkk
Params752M
Context256K
Best fitQ4_K_M 1.4 GB
ReasoningVision
QW
Huihui Qwen3.5 35B A3B Abliterated
Qwen · cs2764
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
ReasoningTool useVision
QW
Qwen2.5 Coder 32B
Qwen · lmstudio-community
Params32.8B
Context32K
Best fitQ8_0 37.5 GB
Coding
EM
Source Hf Embeddinggemma 2
Embeddinggemma · ngquocvinh
Params271M
Context256K
Best fitQ6_K 2.4 GB
EmbeddingVision
LF
LFM2.5 24B A2B Uncensored Heretic
Lfm · mradermacher
Params24B
Context128K
Best fitQ6_K 22.9 GB
GGUF
WI
WizardLM 30B Uncensored Guanaco SuperCOT 30b i1
Wizardlm · mradermacher
Params32.5B
Context2K
Best fitQ6_K 40.3 GB
GGUF
QW
Qwen3.8-27B
Qwen · kingjones777
Params26.9B
Context256K
Best fitQ6_0 27.5 GB
Vision
JA
Jais-3-32B
Jais · mradermacher
Params34.8B
Context512K
Best fitQ6_K 31.2 GB
Reasoning
DA
DanTagGen alpha
Dantaggen · KBlueLeaf
Params393M
Context512
Best fitF16 2.1 GB
GGUF
QW
Qwen2.5 VL 32B Instruct Abliterated
Qwen · mradermacher
Params32.8B
Context125K
Best fitQ6_K 29.5 GB
Vision

Other memory sizes

Keep browsing