PA

patched mix 4x7B

PatchedGGUF by patched-codesUpdated 2024-04-09
Download on Hugging Face
Parameters19.1B
Context4K
Layers30
Architecturellama
Smallest quant6.6 GB
Quick answer

patched mix 4x7B needs about 15.4 GB of memory at Q4_K_M (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 6.6 GB (Q2_K) to 10.9 GB (Q4_K_M).

patched mix 4x7B is a 19.1B-parameter Patched model in GGUF format, quantized by patched-codes. Its trained context length is 4K tokens. The repository has 2 quant files, from 6.6 GB (Q2_K) to 10.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.6 GB 9.1 GB
Too big Get file →
Q4_K_M10.9 GB 13.4 GB
Too big Get file →

What GPU do you need for patched mix 4x7B?

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: the best quant that fits is Q2_K (6.6 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (10.9 GB file, about 15.4 GB in use).

Which patched mix 4x7B quant should you choose?

Q4_K_M is the usual starting point for patched mix 4x7B: it balances file size and quality well. Here it is a 10.9 GB file.

If memory is tight, the smallest file is Q2_K at 6.6 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
Parameters19.1B (approximate, mixture of experts)
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized bypatched-codes
FamilyPatched
Downloads (HF)38
Last updated2024-04-09

Frequently asked questions about patched mix 4x7B

How much VRAM does patched mix 4x7B need?

About 15.4 GB at Q4_K_M with an 8K context window. That is the 10.9 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 patched mix 4x7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of patched mix 4x7B GGUF?

It depends on the quant: Q2_K is 6.6 GB, Q4_K_M is 10.9 GB.

What context length does patched mix 4x7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

Where can I download patched mix 4x7B GGUF?

The files are on Hugging Face in the patched-codes/patched-mix-4x7B-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 patched-codes

All by patched-codes →

Other medium models

All medium models →