DI

DictaLM 3.0 24B Thinking FP8

DictalmGGUF by VRDateUpdated 2025-12-04
Download on Hugging Face
Parameters23.6B
Context64K
Layers40
Architecturellama
Smallest quant13.4 GB
Quick answer

DictaLM 3.0 24B Thinking FP8 needs about 15.3 GB of memory at Q4_0 (a 13.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

DictaLM 3.0 24B Thinking FP8 is a 23.6B-parameter Dictalm model in GGUF format, quantized by VRDate. Its trained context length is 64K tokens. The repository has 1 quant file, from 13.4 GB (Q4_0) to 13.4 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_013.4 GB 15.3 GB
Too big Get file →

What GPU do you need for DictaLM 3.0 24B Thinking FP8?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_0 (13.4 GB file, about 15.3 GB in use).

Which DictaLM 3.0 24B Thinking FP8 quant should you choose?

Q4_0 (13.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context65,280 tokens
KV cache (fp16)160 KB per token

Source

Quantized byVRDate
FamilyDictalm
Licenseapache-2.0
Downloads (HF)25
Last updated2025-12-04

Frequently asked questions about DictaLM 3.0 24B Thinking FP8

How much VRAM does DictaLM 3.0 24B Thinking FP8 need?

About 15.3 GB at Q4_0 with an 8K context window. That is the 13.4 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 DictaLM 3.0 24B Thinking FP8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DictaLM 3.0 24B Thinking FP8 GGUF?

It depends on the quant: Q4_0 is 13.4 GB.

What context length does DictaLM 3.0 24B Thinking FP8 support?

The GGUF header lists a trained context length of 65,280 tokens (64K). 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 DictaLM 3.0 24B Thinking FP8 GGUF?

The files are on Hugging Face in the VRDate/DictaLM-3.0-24B-Thinking-FP8-Q4_0-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 DictaLM 3.0 24B Thinking FP8 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.

Other GGUFs of DictaLM-3.0-24B-Thinking-FP8

Similar models

Browse all →

More from VRDate

All by VRDate →

More Dictalm models

All Dictalm →

Other medium models

All medium models →