Dolphin-Mistral-24B-Venice-Edition
Website: https://dphn.ai Twitter: https://x.com/dphnAI Web Chat: https://chat.dphn.ai Telegram bot: https://t.me/DolphinAIbot
Params
24.0 B
Context
—
Downloads 30d
333 K
Likes
703
Download history
daily snapshots · 56 days
▲ 72 K in the last 30 days (27.5%)
609 K289 K
Aug 23Sep 2Sep 12Sep 21
609 K181 K
Jul 28Aug 15Sep 3Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 48.0 GB | 56.9 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/dolphin-mistral-24b-venice-edition
{
"hf_id": "dphn/Dolphin-Mistral-24B-Venice-Edition",
"params_b": 24.01,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 332653,
"vram_estimates": [
{ "quant": "bf16", "gb": 56.9 }
],
"updated_at": "2026-07-28T18:08:07Z"
}
Specifications
- Architecture
- Mistral3ForConditionalGeneration
- Parameters
- 24.0 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2025-06-12
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-generation model