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
Qwen3.8 35B A3B Distill
Qwen · mradermacher
Params35.5B
Context256K
Best fitQ8_0 39.0 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next
Qwen · TonyMFJ
Params51.2B
Context256K
Q4_K_M2.8 GB
Vision
MI
Mistral-Large-4-1T-A52B-DSpark
Mistral · unsloth
Params1050B
Context1024K
Best fitBF16 4.8 GB
ReasoningTool useVision
MI
Codestral 22B v0.1 IMat
Mistral · legraphista
Params22.2B
Context32K
Best fitBF16 46.9 GB
Coding
QW
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · CCSSNE
Params34.7B
Context256K
Best fitQ8_K 44.8 GB
Vision
QW
Qwen3.5 122B A10B Heretic
Qwen · mradermacher
Params122B
Context256K
Best fitQ2_K 45.9 GB
GGUF
QW
Sperma Aj Qwen3.8 27b
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
Roleplay
SK
Sketch Cydonia 24B V1.3
Sketch · mradermacher
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
Roleplay
QW
Qwopus3.6 35B A3B Coder APEX
Qwopus · mudler
Params34.7B
Context256K
Smallest13.5 GB
CodingVision
OL
Olmo-3-7B-Think
OLMo · unsloth
Params7.3B
Context64K
Best fitBF16 19.4 GB
Reasoning
JI
jina embeddings v4 text retrieval
Jina · jinaai
Params3.1B
Context125K
Best fitF16 7.0 GB
EmbeddingVision
QW
Swift Qwen3.8 27B Uncensored Dynamic MTP
Qwen · ajgazin
Params461M
Context256K
Best fitQ8_K_XL 34.1 GB
Vision
MU
Muse Glimmer 30B
Muse · AaryanK
Params28B
Context128K
Best fitQ8_K_XL 35.9 GB
Vision
SL
Slimaki Tavern 24B v1.3
Slimaki · mradermacher
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
ReasoningRoleplay
GL
Glm 4 9b Chat
GLM · bartowski
Params9.4B
Context128K
Best fitQ8_0 10.8 GB
GGUF
LL
Llm Jp 4.1 8b Thinking
Llm · llm-jp
Params8.59B
Context64K
Best fitBF16 18.8 GB
Reasoning
QW
Qwen3 gabliterated image generation
Qwen · goonsai-com
Params4B
Context256K
Best fitQ8_0 6.0 GB
GGUF
LL
phind_phind-codellama-34b-v2
Llama · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
Coding
GR
Granite-4.1-8B
Granite · unsloth
Params8.79B
Context128K
Best fitBF16 19.4 GB
GGUF
TO
Tongyi DeepResearch 30B A3B
Tongyi · bartowski
Params30.5B
Context128K
Best fitQ8_0 33.8 GB
GGUF
YI
01 ai Yi 34B
Yi · RichardErkhov
Params34.4B
Context4K
Best fitQ8_0 39.1 GB
GGUF
QW
Qwen3.8-27B
Qwen · haybar4k
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
ReasoningTool useVision
GE
Gemma 3 1b
Gemma · lmstudio-community
Params1B
Context32K
Best fitQ4_0 1.4 GB
GGUF
FA
90m Instruct
Falcon · tiiuae
Params91M
Context256K
Best fitBF16 0.8 GB
GGUF
SE
Seed-Coder-8B-Reasoning
Seed · unsloth
Params8.25B
Context64K
Best fitBF16 18.1 GB
CodingReasoning
QW
Qwen3.5 9B Heretic Ara v1
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ6_K 9.0 GB
GGUF
HE
Hemmingway 1 Heretic With Mtp Bf16
Hemmingway · Abiray
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
GGUF
QW
Qwen3.5 35B A3B Heretic
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
GGUF
LL
archangel_sft-kto_llama30b
Llama · mradermacher
Params32.5B
Context2K
Best fitQ6_K 40.3 GB
GGUF
MI
Ministral 3 14B Abliterated
Mistral · mradermacher
Params13.5B
Context256K
Best fitQ8_0 16.2 GB
Tool use

Other memory sizes

Keep browsing