GGUF models that fit in 32 GB
198257 GGUF language models have at least one quant whose estimated memory use is 32 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.
PH
phi 2
Phi · TheBloke
Params2.78B
Context2K
Best fitQ8_0 6.1 GB
ME
Melody1437 26B A4B v2.0
Melody · ReadyArt
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
QW
Qwen3.8 27B Uncensored Chinese
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
QW
qwen image 2.1 comfy
Qwen · t8star
Params8.95B
Context256K
Best fitQ4_K_M 7.5 GB
DE
DeepSeek R1 Distill Llama 70B
DeepSeek · bartowski
Params70.6B
Context128K
Best fitIQ3_XXS 30.7 GB
LL
Llama 3.2 11B Vision Instruct
Llama · leafspark
Params9.78B
Context128K
Best fitF16 21.4 GB
FL
Flint
Flint · ggml-org
Params39.8B
Context256K
Best fitQ4_K_M 24.7 GB
QW
Qwen2.5 VL 32B Instruct Unredacted MAX
Qwen · mradermacher
Params32.8B
Context125K
Best fitQ6_K 29.5 GB
MI
MiniCPM V 2 6
MiniCPM · openbmb
Params7.61B
Context32K
Best fitF16 16.2 GB
QW
Qwen3.8 27B Uncensored Heretic Abliterated
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
OR
Huihui Ornith 1.0 9B abliterated MTP
Ornith · huihui-ai
Params2.28B
Context256K
Best fitBF16 20.0 GB
LL
Dolphin 3.0 Llama 3.2 3B
Llama · bartowski
Params3.21B
Context128K
Best fitF32 14.3 GB
LF
LFM2 700M
Lfm · LiquidAI
Params742M
Context125K
Best fitF16 2.8 GB
LL
Meta llama_Meta Llama 3 70B Instruct
Llama · ThomasBaruzier
Params70.6B
Context8K
Best fitIQ3_XXS 30.7 GB
DE
DeepSeek Coder V2 Lite Instruct Abliterated
DeepSeek · mradermacher
Params15.7B
Context160K
Best fitQ6_K 15.1 GB
LY
Lythri 4B A2B
Lythri · mradermacher
Params4.63B
Context128K
Best fitQ6_K 4.9 GB
GL
Huihui GLM 4.7 Flash Abliterated
GLM · mradermacher
Params30B
Context198K
Best fitQ6_K 26.0 GB
TA
UI TARS 1.5 7B
Tars · mradermacher
Params7.62B
Context125K
Best fitF16 16.2 GB
XI
Xiaomi OCR 0
Xiaomi · prithivMLmods
Params752M
Context256K
Best fitBF16 2.4 GB
GE
Gemma 3 4B VL It Gemini Pro Heretic Uncensored Thinking
Gemma · Andycurrent
Params3.88B
Context128K
Best fitF16 9.4 GB
IN
Ingot XII 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest5.9 GB
GR
Granite 4.1 8b
Granite · ibm-granite
Params8.79B
Context128K
Best fitBF16 19.4 GB
QW
Qwen3.8 27B Uncensored Heretic v3
Qwen · OS-Software
Params27B
Context256K
Best fitQ6_K_XL 27.6 GB
QW
qwen2-0_5b-instruct
Qwen · Qwen
Params494M
Context32K
Q4_K_M0.4 GB
QW
Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
QW
Qwen2.5 Coder 3B Instruct Abliterated
Qwen · bartowski
Params3.09B
Context32K
Best fitF16 7.0 GB
GP
OpenAI Gpt Oss 20B Claude 4.5 Opus Heretic Uncensored
gpt-oss · mradermacher
Params20.9B
Context128K
Best fitQ6_K 23.1 GB
QW
Qwen2.5 Coder 7B Instruct Uncensored
Qwen · BlossomsAI
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
MI
Mistral 7B Instruct v0.2 llamafile
Mistral · mozilla-ai
Params7.24B
Context32K
Best fitBF16 16.1 GB
GE
Gemma The Writer N Restless Quill 10B
Gemma · DavidAU
Params10B
Context8K
Best fitQ8_0 15.1 GB