utOpenAI · Downloadable
gpt-oss-20b
Generates text for conversations and writing.
- Source listed
- Aug 4, 2025
- Parameters
- 20B
- 4-bit weights only
- ≈ 10 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 rankingOpenAI · Downloadable
gpt-oss-safeguard-20b
Generates text for conversations and writing.
- Source listed
- Sep 18, 2025
- Parameters
- 20B
- 4-bit weights only
- ≈ 10 GB
- License
- apache-2.0
Z.ai · Downloadable
cogvlm2-llama3-chat-19B
Generates text for conversations and writing.
- Source listed
- May 16, 2024
- Parameters
- 19B
- 4-bit weights only
- ≈ 9.5 GB
- License
- other
Z.ai · Downloadable
cogvlm2-llama3-chat-19B-int4
Generates text for conversations and writing.
- Source listed
- May 24, 2024
- Parameters
- 19B
- 4-bit weights only
- ≈ 9.5 GB
- License
- other
Z.ai · Downloadable
cogvlm2-llama3-chat-19B-tgi
Generates text for conversations and writing.
- Source listed
- Jun 8, 2024
- Parameters
- 19B
- 4-bit weights only
- ≈ 9.5 GB
- License
- other
Z.ai · Downloadable
cogvlm2-llama3-chinese-chat-19B
Generates text for conversations and writing.
- Source listed
- May 16, 2024
- Parameters
- 19B
- 4-bit weights only
- ≈ 9.5 GB
- License
- other
Z.ai · Downloadable
cogvlm2-llama3-chinese-chat-19B-int4
Generates text for conversations and writing.
- Source listed
- May 24, 2024
- Parameters
- 19B
- 4-bit weights only
- ≈ 9.5 GB
- License
- other
Z.ai · Downloadable
cogvlm2-llama3-chinese-chat-19B-tgi
Generates text for conversations and writing.
- Source listed
- Jun 8, 2024
- Parameters
- 19B
- 4-bit weights only
- ≈ 9.5 GB
- License
- other
Meta · Downloadable
Llama-4-Maverick-17B-128E
Understands text and images and responds in text.
- Source listed
- Apr 2, 2025
- Parameters
- 17B
- 4-bit weights only
- ≈ 8.5 GB
- License
- other
Meta · Downloadable
Llama-4-Maverick-17B-128E-Instruct
Understands text and images and responds in text.
- Source listed
- Apr 1, 2025
- Parameters
- 17B
- 4-bit weights only
- ≈ 8.5 GB
- License
- other
Meta · Downloadable
Llama-4-Scout-17B-16E
Understands text and images and responds in text.
- Source listed
- Apr 2, 2025
- Parameters
- 17B
- 4-bit weights only
- ≈ 8.5 GB
- License
- other
Meta · Downloadable
Llama-4-Scout-17B-16E-Instruct
Understands text and images and responds in text.
- Source listed
- Apr 2, 2025
- Parameters
- 17B
- 4-bit weights only
- ≈ 8.5 GB
- License
- other
DeepSeek · Downloadable
deepseek-moe-16b-base
Generates text for conversations and writing.
- Source listed
- Jan 8, 2024
- Parameters
- 16B
- 4-bit weights only
- ≈ 8 GB
- License
- other
DeepSeek · Downloadable
deepseek-moe-16b-chat
Generates text for conversations and writing.
- Source listed
- Jan 9, 2024
- Parameters
- 16B
- 4-bit weights only
- ≈ 8 GB
- License
- other
Moonshot AI · Downloadable
Moonlight-16B-A3B
Generates text for conversations and writing.
- Source listed
- Feb 22, 2025
- Parameters
- 16B
- 4-bit weights only
- ≈ 8 GB
- License
- mit
Moonshot AI · Downloadable
Moonlight-16B-A3B-Instruct
Generates text for conversations and writing.
- Source listed
- Feb 22, 2025
- Parameters
- 16B
- 4-bit weights only
- ≈ 8 GB
- License
- mit
Microsoft · Downloadable
Phi-4-reasoning-vision-15B
Understands text and images and responds in text. Supports a reasoning mode.
- Source listed
- Jan 23, 2026
- Parameters
- 15B
- 4-bit weights only
- ≈ 7.5 GB
- License
- mit
DeepSeek · Downloadable
DeepSeek-R1-Distill-Qwen-14B
Generates text for conversations and writing. Supports a reasoning mode.
- Source listed
- Jan 20, 2025
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- mit
Microsoft · Downloadable
FrogMini-14B-2510
Generates text for conversations and writing.
- Source listed
- Jan 9, 2026
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- mit
Microsoft · Downloadable
NextCoder-14B
Designed for coding and software tasks. Generates text for conversations and writing.
- Source listed
- May 3, 2025
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- mit
NVIDIA · Downloadable
Nemotron-Labs-Diffusion-14B
Generates text for conversations and writing.
- Source listed
- Apr 22, 2026
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- other
NVIDIA · Downloadable
Nemotron-Labs-Diffusion-14B-Base
Generates text for conversations and writing.
- Source listed
- Apr 23, 2026
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- other
Qwen · Alibaba · Downloadable
Qwen3-14B
Generates text for conversations and writing.
- Source listed
- May 23, 2025
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen3-14B-MLX
Generates text for conversations and writing.
- Source listed
- Jun 12, 2025
- Parameters
- 14B
- 4-bit weights only
- ≈ 7 GB
- License
- apache-2.0
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