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.
LF
Lfm2.5-1.2B-Instruct
Lfm · unsloth
Params1.17B
Context125K
Best fitBF16 3.9 GB
DI
diffusiongemma 26B A4B it
Diffusiongemma · unsloth
Params25.3B
Context256K
Best fitQ6_K 31.2 GB
QW
LFM2.5 2.6B
Qwen · DavidAU
Params2.7B
Context128K
Best fitBF16 7.9 GB
QW
Qwen3.8 Flash Next GSQ RCO
Qwen · pfeifferj
Params125B
Context256K
Best fitQ4_0 30.8 GB
QW
Qwen Image 2.1 PE MTP
Qwen · mozophe
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
SE
Sentence Bert Swedish Cased
Sentence · KBLab
Params124M
Context512
Best fitBF16 1.1 GB
SM
SmolVLM 500M Instruct
Smolvlm · ggml-org
Params409M
Context8K
Best fitF16 1.7 GB
LL
Meta Llama 3.1 70B Instruct
Llama · bartowski
Params70.6B
Context128K
Best fitQ2_K_L 30.6 GB
QW
Qwen3.5 9B Abliterated
Qwen · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
MI
Mistral-7B-Instruct-v0.3
Mistral · bartowski
Params7.25B
Context32K
Best fitF32 30.6 GB
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · mlabonne
Params8B
Context128K
Best fitBF16 17.6 GB
QW
MiMo V2.6 Distill Qwen 9B Ablitrated
Qwen · Hikari07jp
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen3 Coder Next
Qwen · bartowski
Params80B
Context256K
Best fitQ2_K_L 29.8 GB
QW
Qwen3 32B Abliterated
Qwen · RoadToNowhere
Params32.8B
Context40K
Best fitQ4_K_M 22.4 GB
QW
Qwen_Qwen3 VL 4B Instruct
Qwen · lmstudio-community
Params4B
Context256K
Best fitQ8_0 6.0 GB
LL
Llama 3.2 3B Instruct
Llama · hugging-quants
Params3.21B
Context128K
Best fitQ4_K_M 3.5 GB
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · groxaxo
Params25.2B
Context256K
Best fitQ6_K_XL 31.8 GB
QW
Sakura Qwen Image 2.1 Turbo Uncensored
Qwen · webmp3
Params7.12B
Context—
Q4_K_M4.1 GB
QW
qwen2.5-14b-instruct
Qwen · Qwen
Params14.8B
Context128K
Q4_K_M9.0 GB
LF
LFM3 VL 2B
Lfm · LiquidAI
Params1.73B
Context125K
Best fitBF16 5.6 GB
QW
Qwen3.8 Flash CIRU STRIX Orca
Qwen · jcbtc
Params126B
Context256K
Best fitQ8_0 5.5 GB
QW
Qwen2.5 14B Uncensored Instruct
Qwen · bartowski
Params14.8B
Context128K
Best fitF16 31.7 GB
LL
Llama 3.2 8X3B MOE Dark Champion Instruct uncensored abliterated 18.4B
Llama · DavidAU
Params18.4B
Context128K
Best fitQ8_0 21.0 GB
AC
xl_regrind_v1
Acestep · mdmachine
Params4.99B
Context32K
Best fitQ8_0 6.9 GB
QW
Qwen3.6 35B A3B DFlash
Qwen · jcuypers
Params474M
Context256K
Best fitQ4_K_M 0.9 GB
LL
Llama-3.3-70B-Instruct
Llama · unsloth
Params70.6B
Context128K
Best fitIQ3_XXS 30.8 GB
QW
Qwen3 Omni 30B A3B Thinking
Qwen · ggml-org
Params30.5B
Context64K
Best fitQ4_K_M 19.9 GB
MA
madlad400 3b mt
Madlad · google
Params2.94B
Context—
Smallest1.0 GB
FB
fblgit juanako 7b UNA
Fblgit · RichardErkhov
Params7.24B
Context—
Best fitQ4_0 5.1 GB
QW
Qwen3 4b Z Image Turbo AbliteratedV1
Qwen · BennyDaBall
Params4B
Context40K
Best fitF16 9.8 GB