Hy3 vs Qwen3-235B-A22B-Instruct-2507
Specs, VRAM requirements and download trends — updated 24 October 2026.
Qwen · B · Open weights
Params
235.1 B
Context
262,144
30d
141 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Hy3 | Qwen3-235B-A22B-Instruct-2507 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 298.8 B | 235.1 B |
| Architecture | HYV3ForCausalLM | Qwen3MoeForCausalLM |
| Context length | 262,144 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 837,193 | 141,425 |
| Downloads all time | 882 K | 1.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-02 | 2025-07-21 |
| API input price / 1M tokens | $0.13 | $0.09 |
| API output price / 1M tokens | $0.53 | $0.55 |
| Est. cost per 1M input + 1M output tokens | $0.66 | $0.64 |
| Cached input / 1M tokens | $0.033 | — |
| AA Intelligence Index | — | 12 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 128,000 | 16,384 |
| API providers | 5 | 5 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Hy3
$0.66
Qwen3-235B-A22B-Instruct-2507
$0.64
Qwen3-235B-A22B-Instruct-2507 is 1.0× cheaper at list price.
Download trend
Daily snapshots, last 26 days (29 Sep – 24 Oct)
837 K141 K
Hy3
Qwen3-235B-A22B-Instruct-2507
A overtook B on 2 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-235B-A22B-Instruct-2507 · fp16 @ 256K ctx
1,646.2 GB / 24 GB
Hy3 · fp16 @ 256K ctx
2,092.0 GB / 24 GB