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.
LF
LFM2.5 8B A1B DSpark Draft v1
Lfm · LiquidAI
Params328M
Context125K
Best fitF16 1.2 GB
SA
Sarashina2.2 3b Instruct v0.1
Sarashina · mmnga
Params3.36B
Context8K
Best fitQ8_0 5.4 GB
QW
Qwen3 VL Embedding 8B
Qwen · mradermacher
Params7.57B
Context256K
Best fitQ8_0 9.8 GB
JA
NT Java 1.1B
Java · InfosysEnterprise
Params1.24B
Context8K
Q4_K_M0.8 GB
MA
manaca 1b base
Manaca · NANI-Nithin
Params1.72B
Context4K
Best fitBF16 4.4 GB
OP
openbuddy_openbuddy-zephyr-7b-v14.1
Openbuddy · TheBloke
Params7.28B
Context32K
Best fitQ8_0 9.3 GB
QW
Qwen3.5 122B A10B Abliterix
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
QW
Qwen3-30B-A3B-128K
Qwen · unsloth
Params30.5B
Context128K
Best fitIQ2_XXS 11.7 GB
CH
AA Chameleon 7b Plus
Chameleon · mradermacher
Params7B
Context4K
Best fitQ6_K 10.6 GB
QW
Qwen3 4b Z Image Engineer V4
Qwen · BennyDaBall
Params4B
Context40K
Best fitF16 9.8 GB
GE
Gemma 3n E2B It
Gemma · bartowski
Params4.46B
Context32K
Best fitQ8_0 5.8 GB
QW
Huihui Qwen3.8 Flash Next abliterated MTP
Qwen · htdohk
Params177B
Context256K
Best fitBF16 9.1 GB
SU
Sulphur 2 Prompt Enhancer Uncensored
Sulphur · PeppX
Params8.95B
Context256K
Best fitQ4_K_M 7.2 GB
QW
Qwopus3.5 9B v3
Qwen · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
SH
Shadow-Siren-14B-v2-Pruned
Shadow · mradermacher
Params13.8B
Context256K
Q4_K_M9.2 GB
QW
Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Best fitQ6_K 7.2 GB
IN
InternVL3_5 38B
Internvl · bartowski
Params32.8B
Context40K
Best fitIQ2_XXS 11.7 GB
PH
Phi 3 Medium 4k Instruct
Phi · mradermacher
Params14B
Context4K
Best fitQ5_K_S 11.8 GB
QW
Qwen2.5 32B
Qwen · mradermacher
Params32.8B
Context128K
Best fitIQ2_XXS 11.7 GB
LF
LFM2.5 1.2B JP 202606
Lfm · LiquidAI
Params1.17B
Context125K
Best fitF16 3.9 GB
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · nyan-ame
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
QW
Qwen3.8-27B
Qwen · LxBarn
Params27.3B
Context256K
Best fitIQ2_S 11.9 GB
DE
Deepseeker Kunou Qwen2.5 14b i1
DeepSeek · mradermacher
Params14.8B
Context128K
Best fitQ4_1 11.5 GB
QW
Qwopus3.5 27B v3 Abliterated
Qwopus · mradermacher
Params27B
Context256K
Best fitIQ2_S 12.0 GB
ZW
ZwZ2 4B
Zwz · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
QW
Qwen2.5 Coder 3B Instruct
Qwen · bocalan
Params3.09B
Context32K
Best fitQ4_K_M 2.7 GB
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · bartowski
Params8B
Context128K
Best fitQ8_0 10.1 GB
MI
Pixtral
Mistral · ggml-org
Params12.2B
Context1000K
Best fitQ4_K_M 9.3 GB
LL
Meta-Llama-3-8B-Instruct-abliterated-v3
Llama · legraphista
Params8B
Context8K
Best fitQ8_0 10.1 GB
MI
kolibri-vikhr-mistral-0427
Mistral · Vikhrmodels
Params7.6B
Context32K
Best fitQ8_0 9.7 GB