- Services
LensVLM-9B is a 9 billion parameter vision-language model from Apple, built on Qwen3.5-9B-Base. It reads long documents as rendered images at 5x, 10x or 15x compression and uses learned tools to expand only the relevant pages back to full resolution. Apple reports accuracy matching the full-text baseline at roughly 4.3x effective compression and results above retrieval, text-compression and visual-compression baselines up to roughly 10.1x across seven text QA benchmarks. Weights are published on Hugging Face under the Apple Machine Learning Research Model License, with the accompanying code under the Apple Sample Code License.
A solid 9B-parameter dense language model from Apple. A pragmatic middle-ground choice when you need open weights without a flagship-sized footprint. Newly released, so production-readiness is still being shaken out.
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
Access model weights, configuration files, and documentation.
No benchmark data available for this model yet.
See how different quantization levels affect VRAM requirements and quality for this model.
| Format | VRAM Required | Quality | |
|---|---|---|---|
| Q2_K | 4.1 GB | Low | |
| Q4_K_MRecommended | 6.0 GB | Good | |
| Q5_K_M | 6.9 GB | Very Good | |
| Q6_K | 8.0 GB | Excellent | |
| Q8_0 | 10.2 GB | Near Perfect | |
| FP16 | 18.8 GB | Full |
The top devices for this model at 4-bit, ranked by fit and speed.
| Device | Grade | Speed | VRAM |
|---|---|---|---|
| AMD Radeon RX 7700 XTAMD | SS | 57.8 tok/s | 6.0 GB |
| Intel Arc B580Intel | SS | 61.0 tok/s | 6.0 GB |
| NVIDIA GeForce RTX 4070NVIDIA | SS | 67.5 tok/s | 6.0 GB |
| NVIDIA GeForce RTX 4070 SUPERNVIDIA | SS | 67.5 tok/s | 6.0 GB |
| NVIDIA GeForce RTX 5060 Ti 8GBNVIDIA | SS | 60.0 tok/s | 6.0 GB |
Energy cost on Raspberry Pi 5 (8GB) (~4.6 tok/s, Q4_K_M) vs flagship API pricing.
| Source | Cost per 1M tokens |
|---|---|
Local (energy only)LensVLM-9B on Raspberry Pi 5 (8GB) · ~4.6 tok/s · 12W | $0.088 |
GPT-6 SolOpenAI · in $2.00 · out $10.00 | $4.40 |
Claude Opus 5.5Anthropic · in $4.00 · out $20.00 | $8.80 |
Gemini 3.5 FlashGoogle · in $1.50 · out $9.00 | $3.75 |
Grok 4.5xAI · in $2.00 · out $6.00 | $3.20 |
API prices blended at 70% input / 30% output.
Hardware amortisation not included. Run the full ROI calculator for payback math.
Cheapest current cloud rentals with at least 6 GB VRAM, refreshed hourly.
Advertising disclosure: we earn commissions when you shop through the links below.
| Option | Cost / GPU-hour |
|---|---|
NVIDIA GeForce RTX 2080 TiVast.ai · Spot · 11 GB VRAM | $0.04 |
NVIDIA GeForce RTX 4060Vast.ai · Spot · 8 GB VRAM | $0.04 |
NVIDIA GeForce RTX 3060Vast.ai · Spot · 12 GB VRAM | $0.05 |
NVIDIA GeForce RTX 3080 TiVast.ai · Spot · 12 GB VRAM | $0.05 |
NVIDIA GeForce RTX 3060 TiVast.ai · Spot · 8 GB VRAM | $0.05 |
Per-GPU rate across RunPod, the Vast.ai marketplace, DigitalOcean, and Vultr.
Spot tier is interruptible. Plan for restarts when comparing against on-demand prices.
Explore the Provider
Aggregate stats, leaderboard, release timeline, and benchmark coverage across every Apple model we track.
Check which of your devices can run this model and how fast.
Compare hosted per-token prices before you commit to local hardware.
Break-even math for self-hosting, renting a GPU, or paying per token.
Live status for the hosted APIs you might use instead of running this locally.
View on Hugging Face