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
imajev 9b
Qwen · mindchain
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
Vision
QW
Qwen3 4B
Qwen · ggml-org
Params4B
Context40K
Best fitF16 9.8 GB
GGUF
QW
Huihui Qwen3.5 2B Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Best fitF16 4.7 GB
ReasoningTool useVision
MI
Mistral Small 4 119B 2603 Heretic
Mistral · Rioky
Params119B
Context1024K
Best fitIQ3_XXS 46.7 GB
Vision
LF
LFM2 1.2B
Lfm · LiquidAI
Params1.17B
Context125K
Best fitF16 3.9 GB
GGUF
HO
K2-Horizon-MoVA-36B-A4B
Horizon · bartowski
Params37.4B
Context512K
Best fitQ8_0 41.9 GB
GGUF
QW
Qwen3 VL 4B Instruct
Qwen · bartowski
Params4B
Context256K
Best fitBF16 9.8 GB
Vision
JU
Julia-1
Julia · ggml-org
Params144M
Context8K
Best fitBF16 1.1 GB
GGUF
QW
Qwen3 Next 80B A3B Instruct Abliterated
Qwen · mradermacher
Params80B
Context256K
Best fitQ4_K_S 46.8 GB
GGUF
GE
gemma-4-E4B-it
Gemma · TheStageAI
Params7.46B
Context128K
Best fitQ8_0 9.9 GB
GGUF
QW
Qwen3.8 27B
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
Vision
AV
ava lfm25 toolcall
Ava · vitorcalvi
Params1.17B
Context125K
Best fitQ4_0 2.3 GB
GGUF
GL
GLM 5.3 Flash abliterated Maya M
GLM · alesha-pro
Params370B
Context64K
Smallest0.0 GB
Vision
QW
Qwen3 4B Abliterated
Qwen · bartowski
Params4B
Context40K
Best fitBF16 9.8 GB
GGUF
SK
Skyfall 31B v4.2
Skyfall · bartowski
Params31.4B
Context128K
Best fitQ8_0 35.6 GB
GGUF
QW
Qwopus3 5 9B Coder Flash Test2 MTP HF
Qwen · Jackrong
Params9.2B
Context256K
Best fitBF16 20.0 GB
CodingReasoningTool use
NS
NSFW flash
Nsfw · UnfilteredAI
Params2.24B
Context4K
Best fitQ4_K_M 4.0 GB
GGUF
QW
Qwen3.8 35B A3B Distill
Qwen · IsValorum
Params34.7B
Context256K
Smallest1.2 GB
ReasoningTool useVision
ST
StartLux-Decision-v1.1-4B-AutoThink
Startlux · startlux-models
Params4.2B
Context256K
Best fitQ8_0 6.1 GB
ReasoningVision
GE
Gemma 4 31B JANG_4M CRACK F16
Gemma · douyamv
Params30.7B
Context256K
Best fitQ3_K_M 48.0 GB
GGUF
MI
MiniCPM5 2B heretic abliterated
MiniCPM · Abiray
Params2.52B
Context128K
Best fitQ8_0 3.5 GB
GGUF
EM
Embeddinggemma 300m Qat Q4_0 Unquantized
Embeddinggemma · unsloth
Params303M
Context2K
Best fitF32 1.9 GB
Embedding
QW
Qwen3.8-27B
Qwen · kingjones777
Params26.9B
Context256K
Best fitQ8_0 30.9 GB
ReasoningTool useVision
QW
Qwen3.8 27B Abliterated
Qwen · prithivMLmods
Params27B
Context256K
Best fitQ8_0 31.2 GB
ReasoningVision
QW
T-Search-Qwen3.6-35B-A3B
Qwen · t-tech
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
ReasoningTool use
LL
codellama_codellama-34b-instruct-hf
Llama · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
Coding
QW
Qwen2.5 3B Instruct Uncensored
Qwen · mradermacher
Params3.09B
Context32K
Best fitF16 7.0 GB
GGUF
MI
Ministral-3-3B-Reasoning-2512
Mistral · unsloth
Params3.43B
Context256K
Best fitBF16 8.2 GB
ReasoningVision
MI
Ministral 8B Instruct 2410 TEST
Mistral · bartowski
Params8B
Context32K
Best fitF16 17.8 GB
GGUF
NU
NuExtract3
Nuextract · numind
Params4.33B
Context256K
Best fitQ8_0 6.2 GB
ReasoningVision

Other memory sizes

Keep browsing