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.

Most downloadedNewestLargestLongest contextSmallest
GE
Gemma 4 E2B Conversational Uncensored
Gemma · minas2025
Params4.65B
Context128K
Smallest5.0 GB
Vision
LL
llava llama 3 8b v1 1 imat
Llama · city96
Params8B
Context8K
Best fitQ8_0 10.1 GB
Vision
LF
Lfm2.5-230M
Lfm · unsloth
Params230M
Context125K
Best fitBF16 1.4 GB
GGUF
DE
DeepSeek R1 Distill Qwen 14B Heretic
DeepSeek · saidutta69
Params14.8B
Context128K
Best fitQ4_K_M 11.1 GB
ReasoningTool use
VA
VanMach 7B
Vanmach · mradermacher
Params7.71B
Context128K
Best fitQ6_K 7.3 GB
GGUF
BO
Borealis 27b
Borealis · mradermacher
Params27B
Context128K
Best fitIQ1_M 11.5 GB
GGUF
QW
Qwen3.6 21B IQ Ultra Heretic Uncensored Thinking
Qwen · mradermacher
Params20.8B
Context256K
Best fitIQ3_M 11.9 GB
ReasoningRoleplay
SP
Spark X2.6 4B
Spark · mradermacher
Params4.11B
Context1024K
Best fitQ6_K 5.1 GB
ReasoningTool use
AI
aidc-ai-business_marcoroni-7b-v3
Aidc · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Best fitF16 7.0 GB
Vision
RO
RoGemma-7b-Instruct
Rogemma · legraphista
Params8.54B
Context8K
Best fitQ6_K 11.3 GB
GGUF
QW
Qwen2-7B
Qwen · legraphista
Params7.62B
Context128K
Best fitQ8_0 9.1 GB
GGUF
MI
MiniCPM5 1B Agentic Tooluse v3
MiniCPM · ewin-reg
Params1.08B
Context128K
Best fitF16 2.9 GB
Tool use
LL
Llama 3.3 8B Thinking Gemini Flash 11000x 128k
Llama · mradermacher
Params8B
Context128K
Best fitQ6_K 8.2 GB
ReasoningRoleplay
QW
Qwen2.5 Coder 14B n8n Workflow Generator
Qwen · mbakgun
Params14.8B
Context32K
Best fitQ4_K_M 11.1 GB
Coding
QW
qwen2.5 14B roleplay zh Q4 K M
Qwen · TouchNight
Params14.8B
Context32K
Best fitQ4_K_M 11.1 GB
Roleplay
CO
Command A Plus 05 2026
Command · bartowski
Params218B
Context195K
Q4_K_M135.1 GB
GGUF
LL
models--mergekit-community--Llama3-12B-wwe
Llama · MaziyarPanahi
Params13.7B
Context8K
Best fitQ5_K_S 11.9 GB
Tool use
MI
models--automerger--Experiment28T3q-7B
Mistral · MaziyarPanahi
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
MI
MixtralOrochi8x7B i1
Mistral · mradermacher
Params46.7B
Context32K
Best fitIQ1_S 11.6 GB
GGUF
MI
emrgnt-cmplxty_mistral-7b-phibrarian-32k
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
QW
Qwen3 14B GPT 5.2 High Reasoning Distill
Qwen · TeichAI
Params14.8B
Context40K
Best fitQ4_K_M 10.8 GB
Reasoning
MI
Ministral 3 14B Reasoning 2512 Uncensored
Mistral · mradermacher
Params13.5B
Context256K
Best fitQ5_K_M 11.5 GB
ReasoningVision
IN
Internlm2 Math Base 20b
InternLM · mradermacher
Params19.9B
Context8K
Best fitQ3_K_M 11.8 GB
GGUF
QW
Qwen2.5 1.5B Instruct Abliterated
Qwen · mradermacher
Params1.54B
Context32K
Best fitF16 3.8 GB
GGUF
MA
Magnum v4 22b
Magnum · mradermacher
Params22.2B
Context32K
Best fitQ3_K_S 12.0 GB
GGUF
KA
Kataguru Industry MVP 27B v1.1
Kataguru · kataguru
Params26.9B
Context256K
Best fitQ8_0 5.8 GB
ReasoningTool useVision
FA
Falcon3 7B Instruct
Falcon · bartowski
Params7.46B
Context32K
Best fitQ8_0 9.4 GB
GGUF
GR
Granite 4.2 30b
Granite · bartowski
Params29.3B
Context128K
Best fitIQ2_XXS 11.7 GB
ReasoningTool use
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · legraphista
Params15.7B
Context160K
Best fitIQ4_NL 11.7 GB
Coding

Other memory sizes

Keep browsing