Qwen3.6-35B-A3B-FP8 vs DeepSeek-V4-Flash-Vision-Exp
Specs, VRAM requirements and download trends — updated 23 September 2026.
Qwen · A · Open weights
Params
36.0 B
Context
—
30d
3.5 M
apache-2.0 · commercial OK
deepseek-ai · B · Open weights
Params
304.6 B
Context
1,048,576
30d
836 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-FP8 | DeepSeek-V4-Flash-Vision-Exp |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 36.0 B | 304.6 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | DeepseekV4ForCausalLM |
| Context length | — | 1,048,576 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 3,536,337 | 835,578 |
| Downloads all time | 46.7 M | 1.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-15 | 2026-08-31 |
| API input price / 1M tokens | not on OpenRouter | $0.22 |
| API output price / 1M tokens | not on OpenRouter | $0.65 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.86 |
| Cached input / 1M tokens | not on OpenRouter | $0.0069 |
| AA Intelligence Index | not on OpenRouter | 34.8 |
| AA Coding Index | not on OpenRouter | 65 |
| AA Agentic Index | not on OpenRouter | 47.5 |
| Max output tokens | not on OpenRouter | 262,144 |
| API providers | not on OpenRouter | 3 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash-Vision-Exp
$0.86
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
13.5 M836 K
Qwen3.6-35B-A3B-FP8
DeepSeek-V4-Flash-Vision-Exp
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-FP8 · fp16
47.1 GB / 24 GB
DeepSeek-V4-Flash-Vision-Exp · fp16 @ 1024K ctx
6,034.3 GB / 24 GB