utXiaomi MiMo · Downloadable
MiMo-V2.6-Distill-Qwen-9B
Understands text and images and responds in text.
- Source listed
- Sep 21, 2026
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- mit
YOUR MEMORY BUDGET
Local AI models for 12GB VRAM.
Explore models by theoretical weight storage. This shortlist covers available downloadable language models with a known or name-derived parameter count.
10 GBleft for weights at 4-bit
12 GB budget − 2 GB reserve
12 GB budget − 2 GB reserve
The reserve is your assumption, not a measured overhead allowance. The default 2 GB may be too little for your runtime or context length. Results are not confirmed fits and have no verified speed rating. Weight estimates use decimal GB and do not include quantization overhead. For timed results on one 12GB machine, see measured speeds.
978 models within the weight budget
Largest parameter count first · not a quality rankingZ.ai · Downloadable
AutoGLM-Phone-9B
Understands text and images and responds in text.
- Source listed
- Dec 8, 2025
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- mit
Z.ai · Downloadable
AutoGLM-Phone-9B-Multilingual
Understands text and images and responds in text.
- Source listed
- Dec 9, 2025
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- mit
Z.ai · Downloadable
codegeex4-all-9b
Designed for coding and software tasks. Generates text for conversations and writing.
- Source listed
- Jul 5, 2024
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Z.ai · Downloadable
cogagent-9b-20241220
Understands text and images and responds in text.
- Source listed
- Dec 20, 2024
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Z.ai · Downloadable
glm-4-9b
Generates text for conversations and writing.
- Source listed
- Jun 4, 2024
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Z.ai · Downloadable
GLM-4-9B-0414
Generates text for conversations and writing.
- Source listed
- Apr 7, 2025
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- mit
Z.ai · Downloadable
GLM-4.1V-9B-Base
Understands text and images and responds in text.
- Source listed
- Jun 28, 2025
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- mit
Z.ai · Downloadable
GLM-4.1V-9B-Thinking
Understands text and images and responds in text. Supports a reasoning mode.
- Source listed
- Jun 28, 2025
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- mit
Z.ai · Downloadable
GLM-Z1-9B-0414
Generates text for conversations and writing.
- Source listed
- Apr 8, 2025
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- mit
Z.ai · Downloadable
LongCite-glm4-9b
Generates text for conversations and writing.
- Source listed
- Sep 2, 2024
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- Not disclosed
Z.ai · Downloadable
LongReward-glm4-9b-DPO
Generates text for conversations and writing.
- Source listed
- Oct 28, 2024
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Z.ai · Downloadable
LongWriter-glm4-9b
Generates text for conversations and writing.
- Source listed
- Aug 12, 2024
- Parameters
- 9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- Not disclosed
Tencent · Downloadable
POINTS-GUI-G
Understands text and images and responds in text.
- Source listed
- Feb 3, 2026
- Parameters
- 8.9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Tencent · Downloadable
POINTS-Seeker
Generates text for conversations and writing.
- Source listed
- Mar 24, 2026
- Parameters
- 8.9B
- 4-bit weights only
- ≈ 4.5 GB
- License
- other
Datalab · Downloadable
chandra
Understands text and images and responds in text.
- Source listed
- Oct 21, 2025
- Parameters
- 8.8B
- 4-bit weights only
- ≈ 4.4 GB
- License
- openrail
inclusionAI · Downloadable
ArmorOCR
Understands text and images and responds in text.
- Source listed
- Aug 20, 2026
- Parameters
- 8.8B
- 4-bit weights only
- ≈ 4.4 GB
- License
- apache-2.0
Microsoft · Downloadable
UniRG-CXR
Understands text and images and responds in text.
- Source listed
- Mar 19, 2026
- Parameters
- 8.8B
- 4-bit weights only
- ≈ 4.4 GB
- License
- apache-2.0
NVIDIA · Downloadable
nemotron-labs-audio-visual-flamingo-hf
Generates text for conversations and writing.
- Source listed
- Apr 15, 2026
- Parameters
- 8.7B
- 4-bit weights only
- ≈ 4.4 GB
- License
- other
OpenBMB · Downloadable
MiniCPM-V-4_5
Understands text and images and responds in text.
- Source listed
- Aug 24, 2025
- Parameters
- 8.7B
- 4-bit weights only
- ≈ 4.3 GB
- License
- apache-2.0
OpenBMB · Downloadable
MiniCPM-Llama3-V-2_5
Understands text and images and responds in text.
- Source listed
- May 19, 2024
- Parameters
- 8.5B
- 4-bit weights only
- ≈ 4.3 GB
- License
- Not disclosed
BAAI · Downloadable
Emu3-Chat
Generates text for conversations and writing.
- Source listed
- Sep 26, 2024
- Parameters
- 8.5B
- 4-bit weights only
- ≈ 4.2 GB
- License
- apache-2.0
inclusionAI · Downloadable
ViLaSR
Understands text and images and responds in text.
- Source listed
- Jun 1, 2025
- Parameters
- 8.3B
- 4-bit weights only
- ≈ 4.1 GB
- License
- Not disclosed
BAAI · Downloadable
AquilaMed-RL
Generates text for conversations and writing.
- Source listed
- Jun 12, 2024
- Parameters
- 8.2B
- 4-bit weights only
- ≈ 4.1 GB
- License
- other
What changes with a 12GB budget?
With 2 GB set aside, 10 GB remains for weights. At 4-bit that allows up to 20 billion parameters in the theoretical calculation. An 8-billion-parameter model alone needs approximately 4 GB at this precision, before its conversation cache and runtime.
Why might a listed model still fail to load?
Its actual weight format may need more space, the runtime may not support its architecture, or the conversation cache may exceed your reserve. Vision models can also need space for image processing. Check the original model card and measure your exact setup before relying on it.
Read the memory guide and technical sources · Compare two models