utZ.ai · Downloadable
GLM-4-32B-0414
Generates text for conversations and writing.
- Source listed
- Apr 7, 2025
- Parameters
- 32B
- 4-bit weights only
- ≈ 16 GB
- License
- mit
YOUR MEMORY BUDGET
Local AI models for 24GB VRAM.
Explore models by theoretical weight storage. This shortlist covers available downloadable language models with a known or name-derived parameter count.
22 GBleft for weights at 4-bit
24 GB budget − 2 GB reserve
24 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.
405 models within the weight budget
Largest parameter count first · not a quality rankingZ.ai · Downloadable
GLM-4-32B-Base-0414
Generates text for conversations and writing.
- Source listed
- Apr 7, 2025
- Parameters
- 32B
- 4-bit weights only
- ≈ 16 GB
- License
- mit
Z.ai · Downloadable
GLM-Z1-32B-0414
Generates text for conversations and writing.
- Source listed
- Apr 8, 2025
- Parameters
- 32B
- 4-bit weights only
- ≈ 16 GB
- License
- mit
Z.ai · Downloadable
GLM-Z1-Rumination-32B-0414
Generates text for conversations and writing.
- Source listed
- Apr 13, 2025
- Parameters
- 32B
- 4-bit weights only
- ≈ 16 GB
- License
- mit
Z.ai · Downloadable
SWE-Dev-32B
Generates text for conversations and writing.
- Source listed
- Apr 6, 2025
- Parameters
- 32B
- 4-bit weights only
- ≈ 16 GB
- License
- mit
Google · Downloadable
gemma-4-31B
Understands text and images and responds in text.
- Source listed
- Mar 12, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- apache-2.0
Google · Downloadable
gemma-4-31B-it
Understands text and images and responds in text.
- Source listed
- Mar 11, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- apache-2.0
Google · Downloadable
gemma-4-31B-it-qat-q4_0
Understands text and images and responds in text.
- Source listed
- May 1, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- apache-2.0
Google · Downloadable
gemma-4-31B-it-qat-q4_0-unquantized
Understands text and images and responds in text.
- Source listed
- Apr 28, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- apache-2.0
Google · Downloadable
gemma-4-31B-it-qat-q4_0-unquantized-assistant
Understands text and images and responds in text.
- Source listed
- May 29, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- apache-2.0
Google · Downloadable
gemma-4-31B-it-qat-w4a16-ct
Understands text and images and responds in text.
- Source listed
- Jun 4, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- apache-2.0
NVIDIA · Downloadable
Gemma-4-31B-IT
Generates text for conversations and writing.
- Source listed
- Apr 2, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- other
NVIDIA · Downloadable
Ising-Calibration-1.5-31B
Understands text and images and responds in text.
- Source listed
- Jul 13, 2026
- Parameters
- 31B
- 4-bit weights only
- ≈ 15.5 GB
- License
- other
NVIDIA · Downloadable
Muse-Glimmer-30B
Understands text and images and responds in text.
- Source listed
- Aug 27, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- apache-2.0
NVIDIA · Downloadable
Nemotron-Cascade-2-30B-A3B
Generates text for conversations and writing.
- Source listed
- Mar 18, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
NVIDIA · Downloadable
Nemotron-Labs-Audex-30B-A3B
Generates text for conversations and writing.
- Source listed
- Jul 6, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
NVIDIA · Downloadable
Nemotron-Labs-TwoTower-30B-A3B-Base
Generates text for conversations and writing.
- Source listed
- Apr 11, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
NVIDIA · Downloadable
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
Generates text for conversations and writing.
- Source listed
- Aug 4, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
NVIDIA · Downloadable
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base
Generates text for conversations and writing.
- Source listed
- Aug 5, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
NVIDIA · Downloadable
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash
Generates text for conversations and writing.
- Source listed
- Aug 5, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
NVIDIA · Downloadable
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark
Generates text for conversations and writing.
- Source listed
- Aug 5, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
NVIDIA · Downloadable
NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B
Generates text for conversations and writing.
- Source listed
- Apr 14, 2026
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- other
Qwen · Alibaba · Downloadable
Qwen3-30B-A3B
Generates text for conversations and writing.
- Source listed
- Jun 11, 2025
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen3-30B-A3B-Instruct-2507
Generates text for conversations and writing.
- Source listed
- Jul 28, 2025
- Parameters
- 30B
- 4-bit weights only
- ≈ 15 GB
- License
- apache-2.0
What changes with a 24GB budget?
With 2 GB set aside, 22 GB remains for weights. At 4-bit that allows up to 44 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