MY

mychen76 openmixtral 6x7b v2

MychenGGUF by RichardErkhovUpdated 2024-09-22
Download on Hugging Face
Parameters35.4B
Context32K
Layers32
Architecturellama
Smallest quant12.9 GB
Quick answer

mychen76 openmixtral 6x7b v2 needs about 23.0 GB of memory at Q4_K_M (a 21.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 12.9 GB (Q2_K) to 37.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

35.4B parameter openmixtral 6x7b v2 model

mychen76 openmixtral 6x7b v2 is a 35.4B parameter mixture of experts model based on the llama architecture. It supports a 32768 token context window and is released under the apache-2.0 license.

Good at

  • Large context reasoning
  • High parameter count
  • Mixture of experts architecture

Limits

  • No vision support
  • Requires large VRAM for full precision
  • No explicit language support list

Best for

  • Complex text generation
  • Long document summarization
  • Research prototyping

Who it’s for. Developers and researchers needing a high‑capacity language model with extensive context. The model is suitable for applications that can accommodate its memory demands and benefit from its mixture of experts design.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.9 GB 14.5 GB
Too big Get file →
IQ3_XS14.5 GB 16.0 GB
Too big Get file →
Q3_K_S15.3 GB 16.9 GB
Too big Get file →
IQ3_S15.3 GB 16.9 GB
Too big Get file →
IQ3_M15.6 GB 17.1 GB
Too big Get file →
Q3_K17.0 GB 18.5 GB
Too big Get file →
Q3_K_M17.0 GB 18.5 GB
Too big Get file →
Q3_K_L18.4 GB 19.9 GB
Too big Get file →
IQ4_XS19.1 GB 20.7 GB
Too big Get file →
Q4_020.0 GB 21.5 GB
Too big Get file →
Q4_K_S20.1 GB 21.7 GB
Too big Get file →
IQ4_NL20.2 GB 21.7 GB
Too big Get file →
Q4_K21.4 GB 23.0 GB
Too big Get file →
Q4_K_M21.4 GB 23.0 GB
Too big Get file →
Q4_122.2 GB 23.7 GB
Too big Get file →
Q5_024.4 GB 26.0 GB
Too big Get file →
Q5_K_S24.4 GB 26.0 GB
Too big Get file →
Q5_K25.1 GB 26.7 GB
Too big Get file →
Q5_K_M25.1 GB 26.7 GB
Too big Get file →
Q5_126.6 GB 28.2 GB
Too big Get file →
Q6_K29.1 GB 30.6 GB
Too big Get file →
Q8_037.6 GB 39.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (12.93 GB file, 14.5 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (21.44 GB file, 23 GB memory) is a good balance. For 32 GB VRAM, Q5_K_M (25.14 GB file, 26.7 GB memory) offers higher quality.

What GPU do you need for mychen76 openmixtral 6x7b v2?

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 IQ3_XS (14.5 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (22.2 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.1 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.6 GB file, about 39.2 GB in use).

Which mychen76 openmixtral 6x7b v2 quant should you choose?

Q4_K_M is the usual starting point for mychen76 openmixtral 6x7b v2: it balances file size and quality well. Here it is a 21.4 GB file.

The Q8_0 file is 37.6 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 12.9 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
Parameters35.4B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyMychen
Licenseapache-2.0
Downloads (HF)434
Last updated2024-09-22

Frequently asked questions about mychen76 openmixtral 6x7b v2

How much VRAM does mychen76 openmixtral 6x7b v2 need?

About 23.0 GB at Q4_K_M with an 8K context window. That is the 21.4 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 mychen76 openmixtral 6x7b v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mychen76 openmixtral 6x7b v2 GGUF?

It depends on the quant: Q2_K is 12.9 GB, IQ3_XS is 14.5 GB, Q3_K_S is 15.3 GB, IQ3_S is 15.3 GB, IQ3_M is 15.6 GB, Q3_K is 17.0 GB and 16 more.

What context length does mychen76 openmixtral 6x7b v2 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 mychen76 openmixtral 6x7b v2 GGUF?

The files are on Hugging Face in the RichardErkhov/mychen76_-_openmixtral-6x7b-v2-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 mychen76 openmixtral 6x7b v2 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 8 GB VRAM?

Yes, the Q2_K quantization uses 12.93 GB file size and requires approximately 14.5 GB memory at 8k context.

Does this model support image inputs?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mychen models

All Mychen →

Other large models

All large models →