Qwen2.5-Coder-32B-Instruct vs Qwen3.5-122B-A10B-NVFP4
Specs, VRAM requirements and download trends — updated 20 September 2026.
Qwen · A · Open weights
Params
32.8 B
Context
32,768
30d
546 K
apache-2.0 · commercial OK
nvidia · B · Open weights
Params
64.6 B
Context
—
30d
351 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-Coder-32B-Instruct | Qwen3.5-122B-A10B-NVFP4 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 32.8 B | 64.6 B |
| Architecture | Qwen2ForCausalLM | Qwen3_5MoeForConditionalGeneration |
| Context length | 32,768 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 545,627 | 351,083 |
| Downloads all time | 13.7 M | 2.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-11-06 | 2026-05-13 |
| API input price / 1M tokens | $0.66 | not on OpenRouter |
| API output price / 1M tokens | $1.00 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $1.66 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | 6.7 | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 29,491 | not on OpenRouter |
| API providers | 1 | not on OpenRouter |
| Tool calling | No | not on OpenRouter |
| Reasoning mode | No | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen2.5-Coder-32B-Instruct
$1.66
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.7 M241 K
Qwen2.5-Coder-32B-Instruct
Qwen3.5-122B-A10B-NVFP4
A overtook B on 14 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-32B-Instruct · fp16
77.5 GB / 24 GB
Qwen3.5-122B-A10B-NVFP4 · fp16
102.0 GB / 24 GB