utQwen · Alibaba · Downloadable
WebWorld-14B
Generates text for conversations and writing.
- Source listed
- Feb 13, 2026
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- apache-2.0
YOUR MEMORY BUDGET
Local AI models for 16GB VRAM.
Explore models by theoretical weight storage. This shortlist covers available downloadable language models with a known or name-derived parameter count.
14 GBleft for weights at 4-bit
16 GB budget − 2 GB reserve
16 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.
352 models within the weight budget
Largest parameter count first · not a quality rankingMeta · Downloadable
CodeLlama-13b-hf
Designed for coding and software tasks. Generates text for conversations and writing.
- Source listed
- Mar 13, 2024
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- llama2
Meta · Downloadable
CodeLlama-13b-Instruct-hf
Designed for coding and software tasks. Generates text for conversations and writing.
- Source listed
- Mar 13, 2024
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- llama2
Meta · Downloadable
CodeLlama-13b-Python-hf
Designed for coding and software tasks. Generates text for conversations and writing.
- Source listed
- Mar 13, 2024
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- llama2
Meta · Downloadable
Llama-2-13b
Generates text for conversations and writing.
- Source listed
- Jul 9, 2023
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- llama2
Meta · Downloadable
Llama-2-13b-chat
Generates text for conversations and writing.
- Source listed
- Jul 9, 2023
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- llama2
Meta · Downloadable
Llama-2-13b-chat-hf
Generates text for conversations and writing.
- Source listed
- Jul 13, 2023
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- llama2
Meta · Downloadable
Llama-2-13b-hf
Generates text for conversations and writing.
- Source listed
- Jul 13, 2023
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- llama2
Stability AI · Downloadable
StableBeluga-13B
Generates text for conversations and writing.
- Source listed
- Jul 27, 2023
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- Not disclosed
Z.ai · Downloadable
agentlm-13b
Generates text for conversations and writing.
- Source listed
- Oct 8, 2023
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- Not disclosed
Z.ai · Downloadable
apar-13b
Generates text for conversations and writing.
- Source listed
- Jul 22, 2024
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- Not disclosed
Z.ai · Downloadable
LongAlign-13B-64k
Generates text for conversations and writing.
- Source listed
- Jan 29, 2024
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- apache-2.0
Z.ai · Downloadable
LongAlign-13B-64k-base
Generates text for conversations and writing.
- Source listed
- Jan 29, 2024
- Parameters
- 13B
- 4-bit weights only
- ≈ 6.5 GB
- License
- apache-2.0
Google · Downloadable
gemma-3-12b-it
Understands text and images and responds in text.
- Source listed
- Mar 1, 2025
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Google · Downloadable
gemma-3-12b-it-qat-int4-unquantized
Understands text and images and responds in text.
- Source listed
- Apr 9, 2025
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Google · Downloadable
gemma-3-12b-it-qat-q4_0
Understands text and images and responds in text.
- Source listed
- Mar 12, 2025
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Google · Downloadable
gemma-3-12b-it-qat-q4_0-unquantized
Understands text and images and responds in text.
- Source listed
- Apr 8, 2025
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Google · Downloadable
gemma-3-12b-pt
Understands text and images and responds in text.
- Source listed
- Mar 1, 2025
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Google · Downloadable
gemma-3-12b-pt-qat-q4_0
Understands text and images and responds in text.
- Source listed
- Mar 12, 2025
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Google · Downloadable
translategemma-12b-it
Understands text and images and responds in text.
- Source listed
- Jan 12, 2026
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Lightricks · Downloadable
gemma-3-12b-it-qat-q4_0-unquantized
Understands text and images and responds in text.
- Source listed
- Mar 4, 2026
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- gemma
Meta · Downloadable
Llama-Guard-4-12B
Understands text and images and responds in text.
- Source listed
- Apr 23, 2025
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- other
Stability AI · Downloadable
stablelm-2-12b
Generates text for conversations and writing.
- Source listed
- Mar 21, 2024
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- other
Stability AI · Downloadable
stablelm-2-12b-chat
Generates text for conversations and writing.
- Source listed
- Apr 4, 2024
- Parameters
- 12B
- 4-bit weights only
- ≈ 6 GB
- License
- other
What changes with a 16GB budget?
With 2 GB set aside, 14 GB remains for weights. At 4-bit that allows up to 28 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