MI

Base_Edu_Llm_Mixtral

MistralGGUF by RichardErkhovUpdated 2024-08-07
Download on Hugging Face
Parameters29.8B
Context128K
Layers32
Architecturellama
Smallest quant10.9 GB
Quick answer

Base_Edu_Llm_Mixtral needs about 19.6 GB of memory at Q4_K_M (a 18.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 10.9 GB (Q2_K) to 31.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Base_Edu_Llm_Mixtral is a 29.8B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 22 quant files, from 10.9 GB (Q2_K) to 31.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.9 GB 12.5 GB
Too big Get file →
IQ3_XS12.2 GB 13.8 GB
Too big Get file →
Q3_K_S12.9 GB 14.4 GB
Too big Get file →
IQ3_S12.9 GB 14.5 GB
Too big Get file →
IQ3_M13.1 GB 14.7 GB
Too big Get file →
Q3_K14.3 GB 15.8 GB
Too big Get file →
Q3_K_M14.3 GB 15.8 GB
Too big Get file →
Q3_K_L15.5 GB 17.0 GB
Too big Get file →
IQ4_XS16.1 GB 17.6 GB
Too big Get file →
Q4_016.8 GB 18.4 GB
Too big Get file →
Q4_K_S16.9 GB 18.5 GB
Too big Get file →
IQ4_NL17.0 GB 18.5 GB
Too big Get file →
Q4_K18.0 GB 19.6 GB
Too big Get file →
Q4_K_M18.0 GB 19.6 GB
Too big Get file →
Q4_118.7 GB 20.2 GB
Too big Get file →
Q5_020.5 GB 22.1 GB
Too big Get file →
Q5_K_S20.5 GB 22.1 GB
Too big Get file →
Q5_K21.1 GB 22.7 GB
Too big Get file →
Q5_K_M21.1 GB 22.7 GB
Too big Get file →
Q5_122.4 GB 23.9 GB
Too big Get file →
Q6_K24.4 GB 26.0 GB
Too big Get file →
Q8_031.7 GB 33.2 GB
Too big Get file →

What GPU do you need for Base_Edu_Llm_Mixtral?

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 Q3_K (14.3 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_1 (22.4 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (24.4 GB file, about 26.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (31.7 GB file, about 33.2 GB in use).

Which Base_Edu_Llm_Mixtral quant should you choose?

Q4_K_M is the usual starting point for Base_Edu_Llm_Mixtral: it balances file size and quality well. Here it is a 18.0 GB file.

The Q8_0 file is 31.7 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 Q2_K at 10.9 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
Parameters29.8B (approximate, mixture of experts)
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Downloads (HF)160
Last updated2024-08-07

Frequently asked questions about Base_Edu_Llm_Mixtral

How much VRAM does Base_Edu_Llm_Mixtral need?

About 19.6 GB at Q4_K_M with an 8K context window. That is the 18.0 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 Base_Edu_Llm_Mixtral on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Base_Edu_Llm_Mixtral GGUF?

It depends on the quant: Q2_K is 10.9 GB, IQ3_XS is 12.2 GB, Q3_K_S is 12.9 GB, IQ3_S is 12.9 GB, IQ3_M is 13.1 GB, Q3_K is 14.3 GB and 16 more.

What context length does Base_Edu_Llm_Mixtral support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Base_Edu_Llm_Mixtral GGUF?

The files are on Hugging Face in the RichardErkhov/amnae_-_base_edu_llm_mixtral_trained-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other medium models

All medium models →