Ling-3.0-flash-VL
We are introducing Ling-3.0-flash-VL, our next-generation native multimodal model. Built upon Ling-3.0-flash, it brings visual information into the complete process of understanding, reasoning, acting, and verification—advancing beyond image and video perception to solving real-world tasks through vision. With 124B total parameters, only 5.5B activated parameters per token, support for image and video inputs, and a c...
Params
124.8 B
Context
—
Downloads 30d
13 K
Likes
125
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)13 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 249.7 GB | 293.9 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.06
input / 1M
$0.18
output / 1M
$0.012
cached input / 1M
$0.24
1M in + 1M out
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- Providers
- 1
- Cheapest provider
- DeepInfra · $0.06 / $0.18
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 24.6 / 57 / 28.7
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- BailingMoeV3VLForConditionalGeneration
- Parameters
- 124.8 B
- Tensor type
- BF16
- Licence
- mit
- First seen on the Hub
- 2026-09-04
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any image-text-to-text model