GGUF models that fit in 12 GB
171517 GGUF language models have at least one quant whose estimated memory use is 12 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.
QW
Qwen3-4B
Qwen · unsloth
Params4B
Context40K
Best fitBF16 9.8 GB
DA
POCKET 35B
Darwin · FINAL-Bench
Params34.7B
Context256K
Best fitIQ1_M 9.4 GB
QW
Qwen3.8 Flash Next
Qwen · AtomicChat
Params177B
Context256K
Q4_K_M94.5 GB
UM
Umt5 Xxl
Umt · city96
Params5.68B
Context512
Best fitQ8_0 9.8 GB
AD
AdaVaR 3B
Adavar · mradermacher
Params3.09B
Context125K
Best fitF16 7.0 GB
QW
Qwen3.8 2B
Qwen · empero-ai
Params1.94B
Context256K
Best fitBF16 4.8 GB
GE
Gemma-4-E2B-It
Gemma · unsloth
Params4.65B
Context128K
Best fitBF16 10.4 GB
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · unsloth
Params30.5B
Context256K
Best fitIQ2_XXS 11.6 GB
QW
Ternary Bonsai 27B
Qwen · prism-ml
Params3.6B
Context4K
Smallest1.9 GB
GE
Gemma 4 E4B
Gemma · lmstudio-community
Params7.5B
Context128K
Best fitQ8_0 9.9 GB
QW
Qwen3-4B-Instruct-2507
Qwen · unsloth
Params4B
Context256K
Best fitF16 9.8 GB
AP
Apodex 1.1 Mini
Apodex · abenzerps
Params35.5B
Context256K
Best fitIQ1_M 10.0 GB
MO
models moved
Models · ggml-org
Params34M
Context—
Best fitF16 6.7 GB
LA
Laguna S 2.1
Laguna · poolside
Params118B
Context1024K
Best fitBF16 4.3 GB
QW
Qwen3.8 Flash Next Gyro abliterated Huihui
Qwen · agentionai
Params177B
Context256K
Smallest2.7 GB
QW
Qwen3.5-2B
Qwen · unsloth
Params1.88B
Context256K
Best fitBF16 4.7 GB
QW
Qwen3.5 9B Kimi K3 Distilled
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
QW
Qwen3-Vl-4B-Instruct
Qwen · unsloth
Params4B
Context256K
Best fitBF16 9.8 GB
QW
qwen2.5-1.5b-instruct
Qwen · Qwen
Params1.78B
Context32K
Q4_K_M1.1 GB
GE
Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced
Gemma · HauhauCS
Params25.2B
Context256K
Q4_K_M16.8 GB
B1
B1 9B
mradermacher
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
TE
Tess 4 27B
Tess · migtissera
Params27B
Context256K
Best fitQ8_0 5.8 GB
EM
Embeddinggemma 300m
Embeddinggemma · ggml-org
Params308M
Context2K
Best fitQ8_0 1.0 GB
QW
Qwen3.8-27B-DFlash2
Qwen · z-lab
Params1.92B
Context256K
Best fitBF16 4.5 GB
QW
Ternary-Bonsai-2-9B-DFlash2
Qwen · prism-ml
Params2.5B
Context256K
Best fitQ8_0 3.4 GB
LL
Meta Llama 3.1 8B Instruct
Llama · bartowski
Params8B
Context128K
Best fitQ8_0 10.1 GB
OR
Ornith-1.0-9B
Ornith · unsloth
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
QW
Qwen3-30B-A3B-Instruct-2507
Qwen · unsloth
Params30.5B
Context256K
Best fitIQ2_XXS 11.6 GB
BI
BigBang v1
Bigbang · bartowski
Params35.5B
Context256K
Best fitIQ2_XXS 11.4 GB
QW
Qwen Image 2.1 Turbo
Qwen · DogukanUrker
Params7.1B
Context—
Best fitQ8_0 9.0 GB