MI

Dolphin Mistral 24B Venice Edition

MistralGGUF by eaddarioUpdated 2025-07-01
Download on Hugging Face
Parameters23.6B
Context32K
Layers40
Architecturellama
Smallest quant9.3 GB
Quick answer

Dolphin Mistral 24B Venice Edition needs about 14.9 GB of memory at Q4_K_M (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 13 quants, from 9.3 GB (Q3_K_S) to 47.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Dolphin Mistral 24B Venice Edition – a steerable, uncensored LLaMA‑based model

Dolphin Mistral 24B Venice Edition is a 23.6 billion‑parameter LLaMA‑style model. It is designed for general‑purpose use and gives users full control over system prompts and alignment. The model is released under the apache‑2.0 license.

Good at

  • Steerable system prompts
  • Uncensored responses
  • Large context of 32768 tokens

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • No built‑in alignment constraints

Best for

  • Custom chatbot deployments
  • Fine‑tuning for niche applications
  • Enterprise AI integration

Who it’s for. Developers and businesses that need a flexible, open‑source LLM with full control over prompts and alignment. The model is ideal for teams that prefer self‑hosted solutions and want to avoid vendor lock‑in.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S9.3 GB 11.2 GB
Too big Get file →
IQ3_S9.7 GB 11.6 GB
Too big Get file →
IQ3_M10.0 GB 11.9 GB
Too big Get file →
Q3_K_M10.5 GB 12.3 GB
Too big Get file →
Q3_K_L11.4 GB 13.2 GB
Too big Get file →
IQ4_NL12.2 GB 14.1 GB
Too big Get file →
Q4_K_S12.3 GB 14.2 GB
Too big Get file →
Q4_K_M13.1 GB 14.9 GB
Too big Get file →
Q5_K_S14.7 GB 16.5 GB
Too big Get file →
Q5_K_M15.2 GB 17.0 GB
Too big Get file →
Q6_K17.7 GB 19.5 GB
Too big Get file →
Q8_023.1 GB 24.9 GB
Too big Get file →
F1647.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 12.32 GB, estimated 14.2 GB memory). For 16 GB VRAM, Q5_K_M (file size 15.15 GB, estimated 17 GB memory) is suitable. For larger GPUs, Q8_0 (23.07 GB, 24.9 GB memory) offers higher precision.

What GPU do you need for Dolphin Mistral 24B Venice Edition?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ3_M (10.0 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.1 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.7 GB file, about 19.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.1 GB file, about 24.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (23.1 GB file, about 24.9 GB in use).

Which Dolphin Mistral 24B Venice Edition quant should you choose?

Q4_K_M is the usual starting point for Dolphin Mistral 24B Venice Edition: it balances file size and quality well. Here it is a 13.1 GB file.

The Q8_0 file is 23.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 9.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byeaddario
FamilyMistral
Licenseapache-2.0
Downloads (HF)3,112
Last updated2025-07-01

Frequently asked questions about Dolphin Mistral 24B Venice Edition

How much VRAM does Dolphin Mistral 24B Venice Edition need?

About 14.9 GB at Q4_K_M with an 8K context window. That is the 13.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Dolphin Mistral 24B Venice Edition on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dolphin Mistral 24B Venice Edition GGUF?

It depends on the quant: Q3_K_S is 9.3 GB, IQ3_S is 9.7 GB, IQ3_M is 10.0 GB, Q3_K_M is 10.5 GB, Q3_K_L is 11.4 GB, IQ4_NL is 12.2 GB and 7 more.

What context length does Dolphin Mistral 24B Venice Edition support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Dolphin Mistral 24B Venice Edition GGUF?

The files are on Hugging Face in the eaddario/Dolphin-Mistral-24B-Venice-Edition-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Dolphin Mistral 24B Venice Edition use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Dolphin Mistral 24B Venice Edition on 8 GB VRAM?

Yes, with the Q4_K_S quantization the model requires approximately 14.2 GB of VRAM at 8 k context, which is close to 8 GB but may need swapping or a lower context size.

Does the model support vision or image inputs?

No, the model has no vision capabilities and is text‑only.

What license applies to this model?

The model is released under the apache‑2.0 license, allowing free use and modification.

Other GGUFs of Dolphin-Mistral-24B-Venice-Edition

Similar models

Browse all →

More from eaddario

All by eaddario →

More Mistral models

All Mistral →

Other medium models

All medium models →