DI

dillfrescott_trinity-v1.2-x8-moe

DillfrescottGGUF by TheBlokeUpdated 2023-12-31
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant15.6 GB
Quick answer

dillfrescott_trinity-v1.2-x8-moe needs about 28.0 GB of memory at Q4_K_M (a 26.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 8 quants, from 15.6 GB (Q2_K) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

46.7B parameter MoE model in GGUF format

dillfrescott_trinity-v1.2-x8-moe is a 46.7B parameter mixture of experts model. It supports a 32768 token context and is released under Apache-2.0. The model is available in multiple GGUF quantisations.

Good at

  • Large context handling
  • Mixture of experts for specialized tasks
  • LLM chat support

Limits

  • Requires large VRAM for higher quant
  • No vision support
  • Apache-2.0 license

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Custom expert routing

Who it’s for. Developers building local LLM applications that need large context and expert routing. Suitable for users of llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K15.6 GB 17.2 GB
Too big Get file →
Q3_K_M20.4 GB 21.9 GB
Too big Get file →
Q4_026.4 GB 28.0 GB
Too big Get file →
Q4_K_M26.4 GB 28.0 GB
Too big Get file →
Q5_032.2 GB 33.8 GB
Too big Get file →
Q5_K_M32.2 GB 33.8 GB
Too big Get file →
Q6_K38.4 GB 40.0 GB
Too big Get file →
Q8_049.6 GB 51.2 GB
Too big Get file →

For 8GB VRAM the smallest quant (Q2_K) still needs ~17.2GB at 8k context, so it is not feasible. With 16GB VRAM you can use Q4_0 or Q4_K_M (~28GB). For 32GB VRAM, Q5_0 or Q5_K_M (~33.8GB) is appropriate. With 64GB VRAM, Q6_K (~40GB) or Q8_0 (~51.2GB) can be used.

What GPU do you need for dillfrescott_trinity-v1.2-x8-moe?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q3_K_M (20.4 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_0 (26.4 GB file, about 28.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).

Which dillfrescott_trinity-v1.2-x8-moe quant should you choose?

Q4_K_M is the usual starting point for dillfrescott_trinity-v1.2-x8-moe: it balances file size and quality well. Here it is a 26.4 GB file.

The Q8_0 file is 49.6 GB, about 1.9 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 Q2_K at 15.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTheBloke
Licenseapache-2.0
Downloads (HF)1,375
Last updated2023-12-31

Frequently asked questions about dillfrescott_trinity-v1.2-x8-moe

How much VRAM does dillfrescott_trinity-v1.2-x8-moe need?

About 28.0 GB at Q4_K_M with an 8K context window. That is the 26.4 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 dillfrescott_trinity-v1.2-x8-moe on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dillfrescott_trinity-v1.2-x8-moe GGUF?

It depends on the quant: Q2_K is 15.6 GB, Q3_K_M is 20.4 GB, Q4_0 is 26.4 GB, Q4_K_M is 26.4 GB, Q5_0 is 32.2 GB, Q5_K_M is 32.2 GB and 2 more.

What context length does dillfrescott_trinity-v1.2-x8-moe support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download dillfrescott_trinity-v1.2-x8-moe GGUF?

The files are on Hugging Face in the TheBloke/trinity-v1.2-x8-MoE-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 dillfrescott_trinity-v1.2-x8-moe 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 this model on 8GB VRAM?

No, even the smallest quant requires ~17.2GB at 8k context.

Does it support vision?

No vision support is provided.

What license does it use?

Apache-2.0 license.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Dillfrescott models

All Dillfrescott →

Other large models

All large models →