MI

Undi95 Mixtral 4x7B DPO RPChat

MistralGGUF by RichardErkhovUpdated 2024-09-10
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

Undi95 Mixtral 4x7B DPO RPChat needs about 16.2 GB of memory at Q4_K_M (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 2.7 GB (Q4_0) to 25.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Undi95 Mixtral 4x7B DPO RPChat is a 24.2B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 2.7 GB (Q4_0) to 25.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.7 GB 4.3 GB
Fits Get file →
IQ4_XS8.1 GB 9.7 GB
Too big Get file →
Q2_K8.8 GB 10.4 GB
Too big Get file →
IQ3_XS9.9 GB 11.5 GB
Too big Get file →
Q3_K_S10.4 GB 12.0 GB
Too big Get file →
IQ3_S10.5 GB 12.0 GB
Too big Get file →
IQ3_M10.6 GB 12.2 GB
Too big Get file →
Q6_K11.0 GB 12.6 GB
Too big Get file →
Q3_K11.6 GB 13.2 GB
Too big Get file →
Q3_K_M11.6 GB 13.2 GB
Too big Get file →
Q3_K_L12.5 GB 14.1 GB
Too big Get file →
Q4_K_S13.7 GB 15.3 GB
Too big Get file →
IQ4_NL13.8 GB 15.3 GB
Too big Get file →
Q4_K14.6 GB 16.2 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →
Q4_115.1 GB 16.7 GB
Too big Get file →
Q5_016.6 GB 18.2 GB
Too big Get file →
Q5_K_S16.6 GB 18.2 GB
Too big Get file →
Q5_K17.1 GB 18.7 GB
Too big Get file →
Q5_K_M17.1 GB 18.7 GB
Too big Get file →
Q5_118.1 GB 19.7 GB
Too big Get file →
Q8_025.7 GB 27.2 GB
Too big Get file →

What GPU do you need for Undi95 Mixtral 4x7B DPO RPChat?

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: the best quant that fits is Q4_0 (2.7 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (2.7 GB file, about 4.3 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_S (10.5 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ4_NL (13.8 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_1 (18.1 GB file, about 19.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 27.2 GB in use).

Which Undi95 Mixtral 4x7B DPO RPChat quant should you choose?

Q4_K_M is the usual starting point for Undi95 Mixtral 4x7B DPO RPChat: it balances file size and quality well. Here it is a 14.6 GB file.

The Q8_0 file is 25.7 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 Q4_0 at 2.7 GB, with the quality trade-offs that come with fewer bits. 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Downloads (HF)156
Last updated2024-09-10

Frequently asked questions about Undi95 Mixtral 4x7B DPO RPChat

How much VRAM does Undi95 Mixtral 4x7B DPO RPChat need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.6 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 Undi95 Mixtral 4x7B DPO RPChat on an 8 GB GPU?

Yes, with Q4_0: the 2.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Undi95 Mixtral 4x7B DPO RPChat GGUF?

It depends on the quant: Q4_0 is 2.7 GB, IQ4_XS is 8.1 GB, Q2_K is 8.8 GB, IQ3_XS is 9.9 GB, Q3_K_S is 10.4 GB, IQ3_S is 10.5 GB and 16 more.

What context length does Undi95 Mixtral 4x7B DPO RPChat 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 Undi95 Mixtral 4x7B DPO RPChat GGUF?

The files are on Hugging Face in the RichardErkhov/Undi95_-_Mixtral-4x7B-DPO-RPChat-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 Undi95 Mixtral 4x7B DPO RPChat use?

Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other medium models

All medium models →