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.
GL
GLM 5.3 Flash UNCENSORED mlx oQ4e DFlash2
GLM · Solstice-AI
Params1.17B
Context1024K
Best fitBF16 3.0 GB
QW
Qwen2.5 7B Instruct 1M
Qwen · lmstudio-community
Params7.62B
Context986K
Best fitQ8_0 9.1 GB
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · bartowski
Params8B
Context128K
Best fitQ8_0 10.1 GB
QW
qwen3.8 27b abliterated 3.69bpw 12GB MTP
Qwen · soyaakinohara
Params27.3B
Context256K
Smallest12.6 GB
QW
Qwen3 VL 32B Instruct
Qwen · bartowski
Params32.8B
Context256K
Best fitQ6_K_L 29.9 GB
VI
MN Violet Lotus 12B
Violet · mradermacher
Params12.2B
Context128K
Best fitQ8_0 14.9 GB
MI
Ministral-3-8B-Reasoning-2512
Mistral · unsloth
Params8.49B
Context256K
Best fitBF16 18.6 GB
OM
Omega Arsenal 12B
Omega · ReadyArt
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
MI
MiniCPM-V-4.7-1B
MiniCPM · AtomicChat
Params1.01B
Context256K
Best fitQ8_0 2.0 GB
MI
ehartford_dolphin-2.5-mixtral-8x7b
Mistral · TheBloke
Params46.7B
Context32K
Best fitQ4_0 28.0 GB
QW
Qwen2.5 VL 7B Instruct Unredacted MAX
Qwen · mradermacher
Params7.62B
Context125K
Best fitF16 16.2 GB
OP
OpenJev
Openjev · ggml-org
Params27B
Context256K
Best fitQ8_0 31.2 GB
QW
Qwen3 30B A3B Abliterated Erotic
Qwen · mradermacher
Params30.5B
Context40K
Best fitQ6_K 26.4 GB
OC
Occamy 1.0 Abliterated
Occamy · SC117
Params34.7B
Context256K
Best fitQ5_K_M 26.5 GB
GE
Gemma-4-26B-A4B-It
Gemma · mudler
Params25.2B
Context256K
Smallest9.5 GB
QW
Qwen3-4B-Thinking-2507
Qwen · unsloth
Params4B
Context256K
Best fitF16 9.8 GB
TE
Ternary Bonsai 2 27B 262k
Ternary · CaryPalmer
Params27.3B
Context256K
Smallest6.4 GB
GO
Goetia 26B A4B v1.7
Goetia · mradermacher
Params26B
Context256K
Best fitQ6_K 31.8 GB
QW
Qwopus3.6 27B Coder MTP
Qwopus · Jackrong
Params461M
Context256K
Best fitQ8_0 31.7 GB
QW
Qwen3.8 9B Distill Uncensored Heretic
Qwen · petruhonk
Params9.2B
Context256K
Best fitF16 20.0 GB
GE
gemma 2b it
Gemma · google
Params2.51B
Context—
Smallest10.0 GB
PH
phonon 40m de
Phonon · gradium
Params51M
Context—
Smallest0.1 GB
OM
d1-omni-600M
Omni · LiquidAI
Params381M
Context125K
Best fitBF16 1.9 GB
LF
LFM2.5-24B-A2B
Lfm · NANI-Nithin
Params24B
Context128K
Best fitQ8_0 28.7 GB
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · bartowski
Params8B
Context128K
Best fitF16 17.6 GB
OM
OmniCoder 9B
Omnicoder · Tesslate
Params8.95B
Context256K
Best fitBF16 19.5 GB
DE
DeepSeek-V2-Lite
DeepSeek · legraphista
Params15.7B
Context160K
Best fitQ8_0 19.5 GB
QW
Qwen2.5 32B Instruct Abliterated
Qwen · mradermacher
Params32.8B
Context32K
Best fitQ6_K 29.5 GB
QW
Ingot XV 27B Q2
Qwen · dendriteholdings
Params26.9B
Context256K
Smallest5.9 GB
GL
GLM 4.6V Flash
GLM · bartowski
Params9.4B
Context128K
Best fitBF16 19.6 GB