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
Qwen3.5 122B A10B Abliterated
Qwen · mradermacher
Params122B
Context256K
Best fitQ2_K 45.9 GB
Vision
LL
turboderp Cat Llama 3 70B instruct
Llama · RichardErkhov
Params3.3B
Context—
Best fitIQ3_XS 33.3 GB
GGUF
PH
Phi 3.5 Mini instruct_Uncensored
Phi · bartowski
Params3.82B
Context128K
Best fitF16 11.4 GB
GGUF
ZE
huggingfaceh4_zephyr-7b-beta
Zephyr · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
GE
Gemma 3 12b It Heretic
Gemma · DreamFast
Params11.8B
Context128K
Best fitF16 27.3 GB
CodingVision
QW
QwQ 32B Preview
Qwen · bartowski
Params32.8B
Context32K
Best fitQ8_0 37.5 GB
Reasoning
MI
Skyfall 31B v4.2
Mistral · TheDrummer
Params31.4B
Context128K
Best fitQ8_0 35.6 GB
Reasoning
QW
Qwen3.8 27B Max Ablit Heretic
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.8 GB
GGUF
ST
stable code 3b
Stable · stabilityai
Params2.8B
Context16K
Smallest2.0 GB
Coding
MI
MiMo-V2.6-Flash-MOPD
Mimo · ggml-org
Params309B
Context1024K
Best fitBF16 23.1 GB
Vision
GR
Granite-4.0-H-Micro
Granite · unsloth
Params3.2B
Context1024K
Best fitBF16 9.6 GB
GGUF
QW
Qwen3 4B Instruct 2507
Qwen · ggml-org
Params4B
Context256K
Best fitQ8_0 6.0 GB
GGUF
LL
Meta-Llama-3-8B-Instruct-imatrix
Llama · lmstudio-community
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
MI
Mistral Small 24B Instruct 2501 Abliterated
Mistral · bartowski
Params23.6B
Context32K
Best fitQ8_0 26.9 GB
GGUF
WI
Wicked Stuff 12B
Wicked · mradermacher
Params11.9B
Context256K
Best fitQ6_K 23.2 GB
ReasoningTool use
FL
Flint
Flint · AtomicChat
Params39.8B
Context256K
Best fitQ8_0 44.2 GB
CodingReasoningTool use
LL
Llama 3.2 4X3B MOE Hell California Uncensored 10B
Llama · DavidAU
Params9.95B
Context128K
Best fitQ8_0 12.0 GB
Roleplay
AB
ABD3ID CodeMentor
Abd · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
Coding
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · lmstudio-community
Params1.78B
Context128K
Best fitQ8_0 2.6 GB
Reasoning
QW
Qwen3.6-35B-A3B
Qwen · peculiar-ragdoll
Params447M
Context256K
Best fitQ8_K_XL 40.3 GB
ReasoningVision
DE
deepseek llm 7B chat
DeepSeek · TheBloke
Params6.91B
Context4K
Best fitQ8_0 11.9 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · modularai
Params8B
Context128K
Best fitF32 33.7 GB
GGUF
MY
Mythos 9b Unhinged
Mythos · King3Djbl
Params8.19B
Context40K
Best fitF16 18.1 GB
ReasoningRoleplayTool use
MI
Magistral-Small-2509
Mistral · unsloth
Params23.6B
Context128K
Best fitQ8_K_XL 30.8 GB
ReasoningVision
DE
deepseek-ai_deepseek-coder-5.7bmqa-base
DeepSeek · TheBloke
Params5.7B
Context16K
Best fitQ8_0 6.7 GB
Coding
QW
Qwen3.5 27B WebNovel Writer Zh
Qwen · mradermacher
Params27B
Context256K
Best fitQ8_0 31.2 GB
GGUF
CO
Cotype Nano
Cotype · QuantFactory
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
GGUF
MO
moondream2
Moondream · moondream
Params1.42B
Context2K
Best fitF16 5.0 GB
CodingVision
QW
Swift Qwen3.8 Flash Next
Qwen · bartowski
Params177B
Context256K
Q4_K_M125.6 GB
ReasoningVision
QW
Qwen3 VL Embedding 8B
Qwen · VesNFF
Params7.6B
Context256K
Best fitF16 16.9 GB
EmbeddingVision

Other memory sizes

Keep browsing