utGoogle · Downloadable
t5gemma-2b-2b-ul2-it
Generates text for conversations and writing.
- Source listed
- Jun 19, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- gemma
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. For timed results on one 12GB machine, see measured speeds.
1,141 models within the weight budget
Largest parameter count first · not a quality rankingGoogle · Downloadable
txgemma-2b-predict
Generates text for conversations and writing.
- Source listed
- Mar 21, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- other
inclusionAI · Downloadable
SingGuard-2b
Understands text and images and responds in text.
- Source listed
- May 25, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
inclusionAI · Downloadable
SingGuard-NSFA-2B
Understands text and images and responds in text.
- Source listed
- Jul 10, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
inclusionAI · Downloadable
UI-Venus-1.5-2B
Understands text and images and responds in text.
- Source listed
- Feb 9, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
inclusionAI · Downloadable
ZwZ-2B
Understands text and images and responds in text.
- Source listed
- Mar 4, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
Kyutai · Downloadable
CASA-Helium1-VL-2B
Understands text and images and responds in text.
- Source listed
- Dec 10, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-nc-sa-4.0
Kyutai · Downloadable
CASA-Helium1-VL-2B-Shared
Understands text and images and responds in text.
- Source listed
- Aug 26, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-nc-sa-4.0
Kyutai · Downloadable
helium-1-2b
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-books
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-hum
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-life
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-main
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-pop
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-science
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-stem
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
helium-1-2b-wiki
Generates text for conversations and writing.
- Source listed
- Apr 30, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-sa-4.0
Kyutai · Downloadable
Helium1-VL-2B
Understands text and images and responds in text.
- Source listed
- Dec 18, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- cc-by-nc-sa-4.0
LightOn · Downloadable
colgrep-agent-2B
Generates text for conversations and writing.
- Source listed
- Oct 3, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
LightOn · Downloadable
LightOn-rerank-LW-2B
Understands text and images and responds in text.
- Source listed
- Jul 8, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
LightOn · Downloadable
LightOn-rerank-PW-2B
Understands text and images and responds in text.
- Source listed
- Jul 8, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
Liquid AI · Downloadable
d1-2B
Understands text and images and responds in text.
- Source listed
- Oct 24, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- other
Liquid AI · Downloadable
LFM3-VL-2B
Understands text and images and responds in text.
- Source listed
- Oct 19, 2026
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- other
Microsoft · Downloadable
bitnet-b1.58-2B-4T
Generates text for conversations and writing.
- Source listed
- Apr 15, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- mit
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