SmolVLM2-500M-Video-Instruct vs Qwen3.6-35B-A3B-MTP-GGUF
Specs, VRAM requirements and download trends — updated 10 November 2026.
HuggingFaceTB · A · Open weights
Params
510 M
Context
—
30d
1.8 M
apache-2.0 · commercial OK
unsloth · B · Open weights
Params
—
Context
—
30d
2.1 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | SmolVLM2-500M-Video-Instruct | Qwen3.6-35B-A3B-MTP-GGUF |
|---|---|---|
| Parameters | 510 M | — |
| Architecture | SmolVLMForConditionalGeneration | — |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 1,773,711 | 2,108,355 |
| Downloads all time | 9.5 M | 6.5 M |
| Quantizations on the Hub | SAFETENSORS | GGUF |
| Gated | No | No |
| First seen on the Hub | 2025-02-11 | 2026-05-11 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.1 M840 K
SmolVLM2-500M-Video-Instruct
Qwen3.6-35B-A3B-MTP-GGUF
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
SmolVLM2-500M-Video-Instruct · fp16
2.8 GB / 24 GB