Built-in Models

Models in prebuiltAppConfig.model_list. Memory requirements are estimates; context sizes are WebLLM defaults.

173 models

DeepSeek

Model Estimated VRAM Context Type / requirements
DeepSeek-R1-Distill-Qwen-7B-q4f16_1-MLC 5.0 GB 4K LLM
DeepSeek-R1-Distill-Qwen-7B-q4f32_1-MLC 5.8 GB 4K LLM
DeepSeek-R1-Distill-Llama-8B-q4f32_1-MLC 6.0 GB 4K LLM
DeepSeek-R1-Distill-Llama-8B-q4f16_1-MLC 4.9 GB 4K LLM

Llama 3

Llama 2

Model Estimated VRAM Context Type / requirements
Llama-2-7b-chat-hf-q4f32_1-MLC-1k 5.2 GB 1K LLM
Llama-2-7b-chat-hf-q4f16_1-MLC-1k 4.5 GB 1K LLM, shader-f16
Llama-2-7b-chat-hf-q4f32_1-MLC 8.9 GB 4K LLM
Llama-2-7b-chat-hf-q4f16_1-MLC 6.6 GB 4K LLM, shader-f16
Llama-2-13b-chat-hf-q4f16_1-MLC 11.5 GB 4K LLM, shader-f16

Qwen3

Model Estimated VRAM Context Type / requirements
Qwen3-0.6B-q4f16_1-MLC 1.4 GB 4K LLM, low VRAM
Qwen3-0.6B-q4f32_1-MLC 1.9 GB 4K LLM, low VRAM
Qwen3-0.6B-q0f16-MLC 2.2 GB 4K LLM, low VRAM
Qwen3-0.6B-q0f32-MLC 3.8 GB 4K LLM, low VRAM
Qwen3-1.7B-q4f16_1-MLC 2.0 GB 4K LLM, low VRAM
Qwen3-1.7B-q4f32_1-MLC 2.6 GB 4K LLM, low VRAM
Qwen3-4B-q4f16_1-MLC 3.4 GB 4K LLM, low VRAM
Qwen3-4B-q4f32_1-MLC 4.2 GB 4K LLM, low VRAM
Qwen3-8B-q4f16_1-MLC 5.6 GB 4K LLM
Qwen3-8B-q4f32_1-MLC 6.7 GB 4K LLM
Qwen3.5-0.8B-q4f16_1-MLC 1.6 GB 4K LLM, low VRAM
Qwen3.5-0.8B-q4f32_1-MLC 1.8 GB 4K LLM, low VRAM
Qwen3.5-0.8B-q0f16-MLC 2.6 GB 4K LLM, low VRAM
Qwen3.5-2B-q4f16_1-MLC 2.2 GB 4K LLM
Qwen3.5-2B-q4f32_1-MLC 2.5 GB 4K LLM
Qwen3.5-4B-q4f16_1-MLC 3.8 GB 4K LLM
Qwen3.5-4B-q4f32_1-MLC 4.6 GB 4K LLM
Qwen3.5-9B-q4f16_1-MLC 6.3 GB 4K LLM
Qwen3.5-9B-q4f32_1-MLC 7.4 GB 4K LLM

Qwen 2.5

Model Estimated VRAM Context Type / requirements
Qwen2.5-0.5B-Instruct-q4f16_1-MLC 945 MB 4K LLM, low VRAM
Qwen2.5-0.5B-Instruct-q4f32_1-MLC 1.0 GB 4K LLM, low VRAM
Qwen2.5-0.5B-Instruct-q0f16-MLC 1.6 GB 4K LLM, low VRAM
Qwen2.5-0.5B-Instruct-q0f32-MLC 2.6 GB 4K LLM, low VRAM
Qwen2.5-1.5B-Instruct-q4f16_1-MLC 1.6 GB 4K LLM, low VRAM
Qwen2.5-1.5B-Instruct-q4f32_1-MLC 1.8 GB 4K LLM, low VRAM
Qwen2.5-3B-Instruct-q4f16_1-MLC 2.4 GB 4K LLM, low VRAM
Qwen2.5-3B-Instruct-q4f32_1-MLC 2.8 GB 4K LLM, low VRAM
Qwen2.5-7B-Instruct-q4f16_1-MLC 5.0 GB 4K LLM
Qwen2.5-7B-Instruct-q4f32_1-MLC 5.8 GB 4K LLM
Qwen2.5-Coder-0.5B-Instruct-q4f16_1-MLC 945 MB 4K LLM, low VRAM
Qwen2.5-Coder-0.5B-Instruct-q4f32_1-MLC 1.0 GB 4K LLM, low VRAM
Qwen2.5-Coder-0.5B-Instruct-q0f16-MLC 1.6 GB 4K LLM, low VRAM
Qwen2.5-Coder-0.5B-Instruct-q0f32-MLC 2.6 GB 4K LLM, low VRAM
Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLC 1.6 GB 4K LLM
Qwen2.5-Coder-1.5B-Instruct-q4f32_1-MLC 1.8 GB 4K LLM
Qwen2.5-Coder-3B-Instruct-q4f16_1-MLC 2.4 GB 4K LLM, low VRAM
Qwen2.5-Coder-3B-Instruct-q4f32_1-MLC 2.8 GB 4K LLM, low VRAM
Qwen2.5-Coder-7B-Instruct-q4f16_1-MLC 5.0 GB 4K LLM
Qwen2.5-Coder-7B-Instruct-q4f32_1-MLC 5.8 GB 4K LLM
Qwen2.5-Math-1.5B-Instruct-q4f16_1-MLC 1.6 GB 4K LLM, low VRAM
Qwen2.5-Math-1.5B-Instruct-q4f32_1-MLC 1.8 GB 4K LLM, low VRAM

Qwen 2

Model Estimated VRAM Context Type / requirements
Qwen2-0.5B-Instruct-q4f16_1-MLC 945 MB 4K LLM, low VRAM
Qwen2-0.5B-Instruct-q0f16-MLC 1.6 GB 4K LLM, low VRAM
Qwen2-0.5B-Instruct-q0f32-MLC 2.6 GB 4K LLM, low VRAM
Qwen2-1.5B-Instruct-q4f16_1-MLC 1.6 GB 4K LLM, low VRAM
Qwen2-1.5B-Instruct-q4f32_1-MLC 1.8 GB 4K LLM, low VRAM
Qwen2-7B-Instruct-q4f16_1-MLC 5.0 GB 4K LLM
Qwen2-7B-Instruct-q4f32_1-MLC 5.8 GB 4K LLM
Qwen2-Math-1.5B-Instruct-q4f16_1-MLC 1.6 GB 4K LLM, low VRAM
Qwen2-Math-1.5B-Instruct-q4f32_1-MLC 1.8 GB 4K LLM, low VRAM
Qwen2-Math-7B-Instruct-q4f16_1-MLC 5.0 GB 4K LLM
Qwen2-Math-7B-Instruct-q4f32_1-MLC 5.8 GB 4K LLM

Phi

Model Estimated VRAM Context Type / requirements
Phi-3.5-mini-instruct-q4f16_1-MLC 3.6 GB 4K LLM
Phi-3.5-mini-instruct-q4f32_1-MLC 5.4 GB 4K LLM
Phi-3.5-mini-instruct-q4f16_1-MLC-1k 2.5 GB 1K LLM, low VRAM
Phi-3.5-mini-instruct-q4f32_1-MLC-1k 3.1 GB 1K LLM, low VRAM
Phi-3.5-vision-instruct-q4f16_1-MLC 4.4 GB 4K Vision
Phi-3.5-vision-instruct-q4f32_1-MLC 6.9 GB 4K Vision
Phi-4-mini-instruct-q4f16_1-MLC 3.4 GB 4K LLM
Phi-4-mini-instruct-q4f32_1-MLC 4.1 GB 4K LLM
Phi-3-mini-4k-instruct-q4f16_1-MLC 3.6 GB 4K LLM
Phi-3-mini-4k-instruct-q4f32_1-MLC 5.4 GB 4K LLM
Phi-3-mini-4k-instruct-q4f16_1-MLC-1k 2.5 GB 1K LLM, low VRAM
Phi-3-mini-4k-instruct-q4f32_1-MLC-1k 3.1 GB 1K LLM, low VRAM
phi-2-q4f16_1-MLC 3.0 GB 2K LLM, shader-f16
phi-2-q4f32_1-MLC 3.9 GB 2K LLM
phi-2-q4f16_1-MLC-1k 2.1 GB 1K LLM, shader-f16, low VRAM
phi-2-q4f32_1-MLC-1k 2.7 GB 1K LLM, low VRAM
phi-1_5-q4f16_1-MLC 1.2 GB 2K LLM, shader-f16, low VRAM
phi-1_5-q4f32_1-MLC 1.6 GB 2K LLM, low VRAM
phi-1_5-q4f16_1-MLC-1k 1.2 GB 1K LLM, shader-f16, low VRAM
phi-1_5-q4f32_1-MLC-1k 1.6 GB 1K LLM, low VRAM

Gemma

Model Estimated VRAM Context Type / requirements
gemma-4-E2B-it-q4f16_1-MLC 3.3 GB 4K LLM, shader-f16
gemma-4-E2B-it-q4f32_1-MLC 3.8 GB 4K LLM
gemma-2-2b-it-q4f16_1-MLC 1.9 GB 4K LLM, shader-f16
gemma-2-2b-it-q4f32_1-MLC 2.4 GB 4K LLM
gemma-2-2b-it-q4f16_1-MLC-1k 1.5 GB 1K LLM, shader-f16, low VRAM
gemma-2-2b-it-q4f32_1-MLC-1k 1.8 GB 1K LLM, low VRAM
gemma-2-9b-it-q4f16_1-MLC 6.3 GB 4K LLM, shader-f16
gemma-2-9b-it-q4f32_1-MLC 8.2 GB 4K LLM
gemma-2-2b-jpn-it-q4f16_1-MLC 1.9 GB 4K LLM, shader-f16, low VRAM
gemma-2-2b-jpn-it-q4f32_1-MLC 2.4 GB 4K LLM, low VRAM
gemma3-1b-it-q4f16_1-MLC 711 MB 4K LLM, low VRAM
gemma-2b-it-q4f16_1-MLC 1.4 GB 4K LLM, shader-f16
gemma-2b-it-q4f32_1-MLC 1.7 GB 4K LLM
gemma-2b-it-q4f16_1-MLC-1k 1.4 GB 1K LLM, shader-f16, low VRAM
gemma-2b-it-q4f32_1-MLC-1k 1.7 GB 1K LLM, low VRAM

Mistral

Model Estimated VRAM Context Type / requirements
Mistral-7B-Instruct-v0.3-q4f16_1-MLC 4.5 GB 4K LLM, shader-f16
Mistral-7B-Instruct-v0.3-q4f32_1-MLC 5.5 GB 4K LLM
Mistral-7B-Instruct-v0.2-q4f16_1-MLC 4.5 GB 4K LLM, shader-f16
OpenHermes-2.5-Mistral-7B-q4f16_1-MLC 4.5 GB 4K LLM, shader-f16
NeuralHermes-2.5-Mistral-7B-q4f16_1-MLC 4.5 GB 4K LLM, shader-f16
WizardMath-7B-V1.1-q4f16_1-MLC 4.5 GB 4K LLM, shader-f16
Ministral-3-3B-Base-2512-q4f16_1-MLC 2.8 GB 4K LLM, low VRAM
Ministral-3-3B-Base-2512-q4f32_1-MLC 3.4 GB 4K LLM, low VRAM
Ministral-3-3B-Reasoning-2512-q4f16_1-MLC 2.8 GB 4K LLM, low VRAM
Ministral-3-3B-Reasoning-2512-q4f32_1-MLC 3.4 GB 4K LLM, low VRAM
Ministral-3-3B-Instruct-2512-BF16-q4f16_1-MLC 2.8 GB 4K LLM, low VRAM
Ministral-3-3B-Instruct-2512-BF16-q4f32_1-MLC 3.4 GB 4K LLM, low VRAM

SmolLM

Model Estimated VRAM Context Type / requirements
SmolLM3-3B-q4f16_1-MLC 2.0 GB 4K LLM, shader-f16
SmolLM3-3B-q4f32_1-MLC 2.5 GB 4K LLM
SmolLM2-1.7B-Instruct-q4f16_1-MLC 1.7 GB 4K LLM, shader-f16, low VRAM
SmolLM2-1.7B-Instruct-q4f32_1-MLC 2.6 GB 4K LLM, low VRAM
SmolLM2-360M-Instruct-q0f16-MLC 872 MB 4K LLM, shader-f16, low VRAM
SmolLM2-360M-Instruct-q0f32-MLC 1.7 GB 4K LLM, low VRAM
SmolLM2-360M-Instruct-q4f16_1-MLC 376 MB 4K LLM, shader-f16, low VRAM
SmolLM2-360M-Instruct-q4f32_1-MLC 580 MB 4K LLM, low VRAM
SmolLM2-135M-Instruct-q0f16-MLC 360 MB 4K LLM, shader-f16, low VRAM
SmolLM2-135M-Instruct-q0f32-MLC 719 MB 4K LLM, low VRAM

StableLM

Model Estimated VRAM Context Type / requirements
stablelm-2-zephyr-1_6b-q4f16_1-MLC 2.0 GB 4K LLM
stablelm-2-zephyr-1_6b-q4f32_1-MLC 2.9 GB 4K LLM
stablelm-2-zephyr-1_6b-q4f16_1-MLC-1k 1.5 GB 1K LLM, low VRAM
stablelm-2-zephyr-1_6b-q4f32_1-MLC-1k 1.8 GB 1K LLM, low VRAM

TinyLlama

Model Estimated VRAM Context Type / requirements
TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC 697 MB 2K LLM, shader-f16, low VRAM
TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC 840 MB 2K LLM, low VRAM
TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC-1k 675 MB 1K LLM, shader-f16, low VRAM
TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC-1k 796 MB 1K LLM, low VRAM
TinyLlama-1.1B-Chat-v0.4-q4f16_1-MLC 697 MB 2K LLM, shader-f16, low VRAM
TinyLlama-1.1B-Chat-v0.4-q4f32_1-MLC 840 MB 2K LLM, low VRAM
TinyLlama-1.1B-Chat-v0.4-q4f16_1-MLC-1k 675 MB 1K LLM, shader-f16, low VRAM
TinyLlama-1.1B-Chat-v0.4-q4f32_1-MLC-1k 796 MB 1K LLM, low VRAM

RedPajama

Model Estimated VRAM Context Type / requirements
RedPajama-INCITE-Chat-3B-v1-q4f16_1-MLC 2.9 GB 2K LLM, shader-f16
RedPajama-INCITE-Chat-3B-v1-q4f32_1-MLC 3.8 GB 2K LLM
RedPajama-INCITE-Chat-3B-v1-q4f16_1-MLC-1k 2.0 GB 1K LLM, shader-f16, low VRAM
RedPajama-INCITE-Chat-3B-v1-q4f32_1-MLC-1k 2.5 GB 1K LLM, low VRAM

Embedding

Model Estimated VRAM Context Type / requirements
snowflake-arctic-embed-m-q0f32-MLC-b32 1.4 GB — Embedding
snowflake-arctic-embed-m-q0f32-MLC-b4 539 MB — Embedding
snowflake-arctic-embed-s-q0f32-MLC-b32 1023 MB — Embedding
snowflake-arctic-embed-s-q0f32-MLC-b4 239 MB — Embedding

Other

Model Estimated VRAM Context Type / requirements
OLMo-2-1124-7B-Instruct-q4f16_1-MLC 6.3 GB 4K LLM
OLMo-2-1124-7B-Instruct-q4f32_1-MLC 8.9 GB 4K LLM
OLMo-2-0425-1B-Instruct-q4f16_1-MLC 1.7 GB 4K LLM, low VRAM
OLMo-2-0425-1B-Instruct-q4f32_1-MLC 2.4 GB 4K LLM, low VRAM
MiniCPM5-2B-q4f16_1-MLC 1.5 GB 4K LLM, shader-f16
MiniCPM5-2B-q4f32_1-MLC 1.9 GB 4K LLM
LFM2.5-1.2B-Instruct-q4f16_1-MLC 1001 MB 4K LLM, shader-f16, low VRAM
LFM2.5-1.2B-Instruct-q4f32_1-MLC 1.1 GB 4K LLM, low VRAM
LFM2.5-350M-q4f16_1-MLC 532 MB 4K LLM, shader-f16, low VRAM
LFM2.5-350M-q4f32_1-MLC 632 MB 4K LLM, low VRAM

See custom models to use your own model, or request a model.