Qwen2.5-Coder-32B-Instruct vs Dolphin-Mistral-24B-Venice-Edition
Specs, VRAM requirements and download trends — updated 4 September 2026.
Qwen · A · Open weights
Params
32.8 B
Context
32,768
30d
548 K
apache-2.0 · commercial OK
dphn · B · Open weights
Params
24.0 B
Context
—
30d
201 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-Coder-32B-Instruct | Dolphin-Mistral-24B-Venice-Edition |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 32.8 B | 24.0 B |
| Architecture | Qwen2ForCausalLM | Mistral3ForConditionalGeneration |
| Context length | 32,768 | 128,000 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 547,542 | 201,047 |
| Downloads all time | 14.1 M | 1.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-11-06 | 2025-06-12 |
| API input price / 1M tokens | $0.66 | $0.20 |
| API output price / 1M tokens | $1.00 | $0.90 |
| Est. cost per 1M input + 1M output tokens | $1.66 | $1.10 |
| Cached input / 1M tokens | — | — |
| AA Intelligence Index | — | — |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 29,491 | 8,192 |
| API providers | 1 | 1 |
| Tool calling | No | No |
| Reasoning mode | No | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen2.5-Coder-32B-Instruct
$1.66
Dolphin-Mistral-24B-Venice-Edition
$1.10
Dolphin-Mistral-24B-Venice-Edition is 1.5× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.7 M181 K
Qwen2.5-Coder-32B-Instruct
Dolphin-Mistral-24B-Venice-Edition
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Dolphin-Mistral-24B-Venice-Edition · fp16
56.9 GB / 24 GB
Qwen2.5-Coder-32B-Instruct · fp16
77.5 GB / 24 GB