MI

Dolphin3.0 Mistral 24B

MistralGGUF by eaddarioUpdated 2025-05-10
Download on Hugging Face
Parameters23.6B
Context32K
Layers40
Architecturellama
Smallest quant9.8 GB
Quick answer

Dolphin3.0 Mistral 24B 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 9.8 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.

Dolphin3.0 Mistral 24B – a large, instruct‑tuned LLM for local use

Dolphin3.0 Mistral 24B is a 23.6 billion‑parameter model based on the Mistral architecture. It is trained for general‑purpose instruction following, coding, math, and function calling. The model is released under the Apache‑2.0 license and supports a 32 768‑token context window.

Good at

  • General‑purpose instruction following
  • Coding and math reasoning
  • Function calling

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • No external data access

Best for

  • Local chatbots
  • Code generation tools
  • Educational tutoring

Who it’s for. Developers and businesses that need a steerable, local LLM with full control over prompts and data. The model is suitable for applications that require a large context window and general‑purpose instruction handling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S9.8 GB 11.6 GB
Too big Get file →
IQ3_S10.2 GB 12.0 GB
Too big Get file →
Q3_K_M10.4 GB 12.3 GB
Too big Get file →
IQ3_M10.8 GB 12.7 GB
Too big Get file →
Q3_K_L11.0 GB 12.8 GB
Too big Get file →
Q4_K_S12.6 GB 14.5 GB
Too big Get file →
IQ4_NL13.1 GB 14.9 GB
Too big Get file →
Q4_K_M13.1 GB 14.9 GB
Too big Get file →
Q5_K_S14.9 GB 16.8 GB
Too big Get file →
Q5_K_M15.6 GB 17.4 GB
Too big Get file →
Q6_K19.3 GB 21.1 GB
Too big Get file →
Q8_023.0 GB 24.8 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 12.64 GB, ~14.5 GB memory at 8 k context). For 12 GB VRAM, Q5_K_S (14.91 GB, ~16.8 GB memory) or Q4_K_M (13.07 GB, ~14.9 GB memory). For 16 GB VRAM, Q5_K_M (15.58 GB, ~17.4 GB memory) or Q6_K (19.28 GB, ~21.1 GB memory).

What GPU do you need for Dolphin3.0 Mistral 24B?

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_S (10.2 GB file, about 12.0 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 (19.3 GB file, about 21.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.0 GB file, about 24.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (23.0 GB file, about 24.8 GB in use).

Which Dolphin3.0 Mistral 24B quant should you choose?

Q4_K_M is the usual starting point for Dolphin3.0 Mistral 24B: it balances file size and quality well. Here it is a 13.1 GB file.

The Q8_0 file is 23.0 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 9.8 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)2,441
Last updated2025-05-10

Frequently asked questions about Dolphin3.0 Mistral 24B

How much VRAM does Dolphin3.0 Mistral 24B 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 Dolphin3.0 Mistral 24B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dolphin3.0 Mistral 24B GGUF?

It depends on the quant: Q3_K_S is 9.8 GB, IQ3_S is 10.2 GB, Q3_K_M is 10.4 GB, IQ3_M is 10.8 GB, Q3_K_L is 11.0 GB, Q4_K_S is 12.6 GB and 7 more.

What context length does Dolphin3.0 Mistral 24B 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 Dolphin3.0 Mistral 24B GGUF?

The files are on Hugging Face in the eaddario/Dolphin3.0-Mistral-24B-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 Dolphin3.0 Mistral 24B 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 Dolphin3.0 Mistral 24B on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires about 14.5 GB of VRAM at 8 k context, which is within 8 GB if using off‑load or lower batch sizes.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license does the model use?

The model is released under the Apache‑2.0 license.

Other GGUFs of Dolphin3.0-Mistral-24B

Similar models

Browse all →

More from eaddario

All by eaddario →

More Mistral models

All Mistral →

Other medium models

All medium models →