Qwen2.5-Coder-14B-Instruct vs Qwen3-30B-A3B-Instruct-2507-FP8
Specs, VRAM requirements and download trends — updated 4 August 2026.
Qwen · A · Open weights
Params
14.8 B
Context
32,768
30d
1.9 M
apache-2.0 · commercial OK
Qwen · B · Open weights
Params
30.5 B
Context
262,144
30d
182 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-Coder-14B-Instruct | Qwen3-30B-A3B-Instruct-2507-FP8 |
|---|---|---|
| Parameters | 14.8 B | 30.5 B |
| Architecture | Qwen2ForCausalLM | Qwen3MoeForCausalLM |
| Context length | 32,768 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 1,936,983 | 182,236 |
| Downloads all time | 20.0 M | 6.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-11-06 | 2025-07-28 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.5 M137 K
Qwen2.5-Coder-14B-Instruct
Qwen3-30B-A3B-Instruct-2507-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-14B-Instruct · fp16
35.2 GB / 24 GB
Qwen3-30B-A3B-Instruct-2507-FP8 · fp16 @ 256K ctx
181.3 GB / 24 GB