Qwen3.6-35B-A3B-FP8 vs Qwen3.6-35B-A3B
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · A · Open weights
Params
36.0 B
Context
—
30d
4.0 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-FP8 | Qwen3.6-35B-A3B |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 36.0 B | 36.0 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | Qwen3_5MoeForConditionalGeneration |
| Context length | — | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 3,962,067 | 4,209,694 |
| Downloads all time | 49.4 M | 35.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-15 | 2026-04-15 |
| API input price / 1M tokens | not on OpenRouter | $0.10 |
| API output price / 1M tokens | not on OpenRouter | $0.90 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $1.00 |
| Cached input / 1M tokens | not on OpenRouter | $0.025 |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | 41.9 |
| AA Agentic Index | not on OpenRouter | 13.1 |
| Max output tokens | not on OpenRouter | 235,929 |
| API providers | not on OpenRouter | 11 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3.6-35B-A3B
$1.00
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
13.5 M3.1 M
Qwen3.6-35B-A3B-FP8
Qwen3.6-35B-A3B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-FP8 · fp16
47.1 GB / 24 GB
Qwen3.6-35B-A3B · fp16
85.0 GB / 24 GB