LensVLM 9B
Parameters
9B
Context Length
262K
Modality
Text
Architecture
Dense
License
apple-amlr
Release Date
21 Sept 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
262,144 tokens
Consumer
3x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for LensVLM 9B available.
Rankings
Overall Rank
-
Coding Rank
-
About LensVLM 9B
LensVLM 9B is a multimodal vision-language model developed by Apple, built on top of high-capacity language backbones. It is tailored for detailed visual question answering, document comprehension, and grounded multimodal reasoning.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
16
Key-Value Heads
4
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
10,000,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
Yes
Linear Attention Ratio
75.0%
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Auxiliary Parameters
-
Hidden Dimension Size
4,096
Number of Layers
32
FFN Intermediate Size (Dense)
12,288
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
248,320
Resources
About LensVLM
The LensVLM model family developed by Apple.
Other LensVLM Models
- No related models available