Qwen3-Coder-Next-FP8 vs Qwen3-30B-A3B-Instruct-2507
Specs, VRAM requirements and download trends — updated 25 August 2026.
Qwen · A · Open weights
Params
79.7 B
Context
262,144
30d
918 K
apache-2.0 · commercial OK
Qwen · B · Open weights
Params
30.5 B
Context
262,144
30d
1.1 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Coder-Next-FP8 | Qwen3-30B-A3B-Instruct-2507 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 79.7 B | 30.5 B |
| Architecture | Qwen3NextForCausalLM | Qwen3MoeForCausalLM |
| Context length | 262,144 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 917,774 | 1,091,162 |
| Downloads all time | 11.0 M | 18.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-01 | 2025-07-28 |
| API input price / 1M tokens | not on OpenRouter | $0.09 |
| API output price / 1M tokens | not on OpenRouter | $0.30 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.39 |
| Cached input / 1M tokens | not on OpenRouter | — |
| AA Intelligence Index | not on OpenRouter | 7.5 |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 235,929 |
| API providers | not on OpenRouter | 3 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-30B-A3B-Instruct-2507
$0.39
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
2.5 M752 K
Qwen3-Coder-Next-FP8
Qwen3-30B-A3B-Instruct-2507
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-30B-A3B-Instruct-2507 · fp16 @ 256K ctx
214.2 GB / 24 GB
Qwen3-Coder-Next-FP8 · fp16 @ 256K ctx
471.4 GB / 24 GB