Models for 8 GB VRAM

Popular sweet spot for 8 GB GPUs — Q4/Q5 quants for daily local inference. Sorted by Hugging Face downloads. Smallest GGUF file size shown per model.

vcruz305/Hy3-GGUF

vcruz305 · from 4.08 GB · 238,697 downloads

yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

yuxinlu1 · from 4.50 GB · 211,424 downloads

MonsterMMORPG/Wan_GGUF

MonsterMMORPG · from 6.46 GB · 110,120 downloads

ToastyPigeon/Gemma4-Test-GGUFs

ToastyPigeon · from 5.75 GB · 51,646 downloads

satgeze/Hy3-1M-GGUF

satgeze · from 5.66 GB · 14,158 downloads

Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF

Jackrong · from 4.41 GB · 12,677 downloads

AtomicChat/ornith-9b-GGUF

AtomicChat · from 4.84 GB · 10,443 downloads

liodon-ai/Ornith-1.0-35B-GGUF-imatrix-GGUF

liodon-ai · from 6.97 GB · 8,587 downloads

xPhoenix777/Flux-Klein-9b-GGUF-Conversions-NSFW

xPhoenix777 · from 6.04 GB · 7,146 downloads

freakyskittle/kimi-k2.7-code-GGUF

freakyskittle · from 5.91 GB · 6,714 downloads

FINAL-Bench/POCKET-35B-GGUF

FINAL-Bench · from 7.67 GB · 6,077 downloads

vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF

vcruz305 · from 7.67 GB · 4,876 downloads

ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-GGUF

ManniX-ITA · from 7.85 GB · 4,189 downloads

Arki05/North-Mini-Code-1.0-GGUF

Arki05 · from 7.74 GB · 4,110 downloads

liodon-ai/Qwen2.5-14B-Instruct-imatrix-GGUF

liodon-ai · from 4.99 GB · 3,539 downloads

LiquidAI/LFM2-8B-A1B-GGUF

LiquidAI · from 4.41 GB · 3,303 downloads

wepiqx/gemma-4-12B-it-SHQ6-GGUF

wepiqx · from 6.27 GB · 3,270 downloads

PeppX/Ornith-1.0-9B-Uncensored-GGUF

PeppX · from 5.24 GB · 3,149 downloads

ItsMeDevRoland/OpenElla-NovelWriter-8B-MAGNATE-GGUF

ItsMeDevRoland · from 7.95 GB · 2,976 downloads

BigDannyPt/WAN-2.2-SmoothMix-GGUF

BigDannyPt · from 4.93 GB · 2,966 downloads

wepiqx/gemma-4-12B-it-LWQ6-GGUF

wepiqx · from 6.27 GB · 2,799 downloads

mradermacher/Gemma-4-12B-OBLITERATED-GGUF

mradermacher · from 4.50 GB · 2,744 downloads

FINAL-Bench/Ourbox-35B-JGOS-GGUF

FINAL-Bench · from 7.67 GB · 2,741 downloads

DavidAU/TieFighter-Holodeck-Holomax-Mythomax-F1-V1-COMPOS-20B-gguf

DavidAU · from 6.42 GB · 2,647 downloads

ManniX-ITA/gemma-4-A4B-98e-v5-coder-it-GGUF

ManniX-ITA · from 7.29 GB · 2,616 downloads

Em-80/Qwen3-coder-REAP-25B-A3B-Rust-GGUF

Em-80 · from 4.91 GB · 2,385 downloads

joeygambino/joyai-echo-gemma3-12b-encoder-Q8_0-gguf

joeygambino · from 7.31 GB · 2,370 downloads

mradermacher/Gemma-4-12B-it-AEON-Abliterated-K4-BF16-GGUF

mradermacher · from 4.50 GB · 2,243 downloads

FadedRedStar/LFM2.5-8B-A1B-heretic-imatrix-GGUF

FadedRedStar · from 4.51 GB · 2,127 downloads

extraltodeus/Qwen3.5-9B-Nikusui-v1-gguf

extraltodeus · from 5.38 GB · 1,917 downloads

Jackxuanxuan/edwardwallst-Gemma-4-31B-JANG_4M-CRACK-GGUF

Jackxuanxuan · from 6.66 GB · 1,860 downloads

SixVolts/GLM-5.2-ewaste-edition-GGUF

SixVolts · from 5.76 GB · 1,813 downloads

DavidAU/MN-GRAND-23.5B-Gutenberg-UNCENSORED-V2-GLM4.7-Thinking-NEO-Imatrix-GGUF

DavidAU · from 7.87 GB · 1,726 downloads

KikoCis/Ornith-1.0-9B-Ollama-fixed-GGUF

KikoCis · from 4.31 GB · 1,714 downloads

ManniX-ITA/gemma-4-A4B-98e-v3-it-GGUF

ManniX-ITA · from 6.86 GB · 1,657 downloads

liodon-ai/gemma-4-12B-it-imatrix-GGUF

liodon-ai · from 4.07 GB · 1,432 downloads

ManniX-ITA/gemma-4-A4B-109e-it-GGUF

ManniX-ITA · from 7.52 GB · 1,412 downloads

DavidAU/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF

DavidAU · from 5.88 GB · 1,372 downloads

wepiqx/gemma-4-12B-OBLITERATED-SHQ7-GGUF

wepiqx · from 6.34 GB · 1,356 downloads

majentik/gemma-4-E4B-RotorQuant-GGUF-IQ4_XS

majentik · from 4.74 GB · 1,348 downloads

TaQuants/Tema_Q-X4-8B-Thinking-TaQuants-GGUF

TaQuants · from 4.19 GB · 1,325 downloads

mradermacher/STARK-WEB-12B-GGUF

mradermacher · from 4.50 GB · 1,273 downloads

AnkitAI/Parable-Granite-4.1-8B-Claude-Fable-5-GGUF

AnkitAI · from 4.77 GB · 1,133 downloads

FadedRedStar/Anubis-Mini-8B-v1-heretic-imatrix-GGUF

FadedRedStar · from 4.36 GB · 1,092 downloads

Situus/STARK-WEB-12B-gguf

Situus · from 6.87 GB · 1,075 downloads

AbteeXAILab/lumynax-reasoning-deepseek-r1-qwen-7b-gguf

AbteeXAILab · from 4.36 GB · 1,064 downloads

Arki05/BLS-Mini-Code-1.0-GGUF

Arki05 · from 7.74 GB · 1,015 downloads

mradermacher/Mordant-12B-Think-GGUF

mradermacher · from 4.46 GB · 995 downloads

liodon-ai/Grug-12B-imatrix-GGUF

liodon-ai · from 4.07 GB · 992 downloads

Shlok0011/CulinaAI-Qwen2.5-7B-GGUF

Shlok0011 · from 4.36 GB · 928 downloads

wepiqx/Ornith-1.0-9B-ASHQ1-GGUF

wepiqx · from 4.75 GB · 913 downloads

FadedRedStar/Anubis-Mini-8B-v1-heretic-GGUF

FadedRedStar · from 4.58 GB · 910 downloads

smthem/comfy-org-gguf-int4

smthem · from 6.43 GB · 871 downloads

wepiqx/gemma-4-12B-OBLITERATED-LWQ7-GGUF

wepiqx · from 6.34 GB · 852 downloads

DavidAU/Reka-Flash-3-21B-Reasoning-Uncensored-MAX-NEO-Imatrix-GGUF

DavidAU · from 7.63 GB · 849 downloads

majentik/gemma-4-E2B-it-RotorQuant-GGUF-Q8_0

majentik · from 4.63 GB · 817 downloads

mradermacher/Grok-3-reasoning-gemma3-12B-distilled-HF-GGUF

mradermacher · from 4.44 GB · 814 downloads

AnkitAI/Mistral-Heretica-12B-GGUF

AnkitAI · from 6.96 GB · 803 downloads

AbteeXAILab/lumynax-infused-gemma-e4b-text-gguf

AbteeXAILab · from 4.97 GB · 802 downloads

liodon-ai/gemma-4-12B-it-GGUF

liodon-ai · from 4.50 GB · 802 downloads

mradermacher/Neuron-V1-Distill-Qwen2-14B-GGUF

mradermacher · from 5.37 GB · 791 downloads

RemySkye/rwkv7-g1h-13.3b-GGUF

RemySkye · from 5.07 GB · 762 downloads

realrebelai/Boogu-Image-Edit_GGUFs

realrebelai · from 6.37 GB · 724 downloads

AbteeXAILab/lumynax-infused-qwen3-8b-gguf

AbteeXAILab · from 4.68 GB · 722 downloads

FINAL-Bench/POCKET-EN-GGUF

FINAL-Bench · from 4.96 GB · 716 downloads

AbteeXAILab/lumynax-infused-qwen3-text-gguf

AbteeXAILab · from 4.68 GB · 714 downloads

maczzzzzz/Grug-12B-ROCmFP4_FAST-GGUF

maczzzzzz · from 5.91 GB · 711 downloads

sci4ai/Qwen3.6-27B-Ablit-IQ2_XXS-GGUF

sci4ai · from 7.85 GB · 703 downloads

FreedomAISVR/NVIDIA-Nemotron-3-Nano-4B-NVFP4-GGUF

FreedomAISVR · from 4.50 GB · 682 downloads

FINAL-Bench/POCKET-KR-GGUF

FINAL-Bench · from 4.75 GB · 681 downloads

XeyonAI/MN-Helcyon-Northstar-12b-v1.0-GGUF

XeyonAI · from 6.33 GB · 675 downloads

majentik/gemma-4-E4B-RotorQuant-GGUF-Q4_K_M

majentik · from 4.97 GB · 669 downloads

xCloudinfo/xGemable-12B-coder-v1.5-GGUF

xCloudinfo · from 7.10 GB · 666 downloads

rafatho/camus-gguf

rafatho · from 4.58 GB · 643 downloads

cstr/VibeVoice-7B-GGUF

cstr · from 5.74 GB · 625 downloads

agurusantosh/tripmind-curriculum-gguf

agurusantosh · from 4.58 GB · 616 downloads

mradermacher/GoT-R1-14B-GGUF

mradermacher · from 5.36 GB · 608 downloads

agurusantosh/tripmind-distill-gguf

agurusantosh · from 4.58 GB · 606 downloads

AtomicChat/Qwen3.5-9B-GGUF

AtomicChat · from 5.24 GB · 605 downloads

agurusantosh/tripmind-ft-gguf

agurusantosh · from 4.58 GB · 604 downloads

piyawudk/PhishMe-12k-Qwen3.5-4B-P1-CDFT-v2-GGUF

piyawudk · from 4.17 GB · 573 downloads

fzcfweasdferttgg/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic-GGUF

fzcfweasdferttgg · from 4.35 GB · 571 downloads

FadedRedStar/LFM2.5-8B-A1B-heretic-GGUF

FadedRedStar · from 4.80 GB · 558 downloads

DarksitoBest/DRK-Coding-V1-GGUF

DarksitoBest · from 5.38 GB · 552 downloads

AbteeXAILab/lumynax-infused-zephyr-7b-beta-gguf

AbteeXAILab · from 4.07 GB · 546 downloads

m9e/MiniMax-M3-uncensored-RP-LC-Q4HQ-GGUF

m9e · from 4.52 GB · 545 downloads

piyawudk/PhishMe-12k-Qwen3.5-4B-P1-CSFT-v3-GGUF

piyawudk · from 4.17 GB · 517 downloads

mradermacher/gemma-4-12B-uncensored-opus4.7-cot-GGUF

mradermacher · from 4.50 GB · 500 downloads

AbteeXAILab/lumynax-longctx-glm4-9b-chat-1m-gguf

AbteeXAILab · from 5.88 GB · 499 downloads

EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF

EZForever · from 6.26 GB · 498 downloads

AdvancedDataIntelligence/adi-qwen3-8b-glm5.2-general-GGUF

AdvancedDataIntelligence · from 4.68 GB · 491 downloads

AbteeXAILab/lumynax-infused-mistral-7b-v03-gguf

AbteeXAILab · from 4.07 GB · 489 downloads

xCloudinfo/xGemable-12B-coder-v2-fullft-GGUF

xCloudinfo · from 6.87 GB · 481 downloads

AbteeXAILab/lumynax-math-qwen25-math-7b-gguf

AbteeXAILab · from 4.36 GB · 472 downloads

AbteeXAILab/lumynax-infused-olmo2-7b-1124-gguf

AbteeXAILab · from 4.16 GB · 464 downloads

AbteeXAILab/lumynax-reasoning-internlm3-8b-gguf

AbteeXAILab · from 4.99 GB · 461 downloads

katafiek/Katarau-9B-ru-RP-nsfw-GGUF

katafiek · from 5.24 GB · 459 downloads

xiaozhengya/ltx-2.3-GGUF

xiaozhengya · from 6.80 GB · 457 downloads

efficiencyx/Jun-LoRA-v4-12B-GGUF

efficiencyx · from 5.67 GB · 456 downloads

ayushhh1662309/legal-chatbot-llama3-8b-gguf

ayushhh1662309 · from 4.58 GB · 455 downloads

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models