UN

UndiMix v2 13B

UndimixGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

UndiMix v2 13B needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).

UndiMix v2 13B – a 13‑billion‑parameter chat model in GGUF format

UndiMix v2 13B is a 13‑billion‑parameter llama architecture model. It is trained on a 4096‑token context window and released under a cc‑by‑nc‑4.0 license. The model is available in multiple GGUF quantisations for CPU and GPU inference.

Good at

  • Chatting with varied tones
  • Using emojis and playful language
  • Handling 4096‑token context

Limits

  • No vision support
  • cc‑by‑nc‑4.0 license restricts commercial use
  • Requires at least 12.6 GB VRAM for Q2_K

Best for

  • Local chat assistants
  • Story generation with long context
  • Testing different quantisations

Who it’s for. Developers and researchers who need a versatile 13B chat model for local deployment. The model is suitable for non‑commercial projects due to its license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_09.0 GB 12.8 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (5.43 GB file, ~12.6 GB VRAM). For 12 GB VRAM, Q3_K_S (5.66 GB file, ~12.9 GB VRAM). For 16 GB VRAM, Q5_K_M (9.23 GB file, ~16.4 GB VRAM).

What GPU do you need for UndiMix v2 13B?

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 Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which UndiMix v2 13B quant should you choose?

Q4_K_M is the usual starting point for UndiMix v2 13B: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 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 5.4 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
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyUndimix
Downloads (HF)2,270
Last updated2023-09-27

Frequently asked questions about UndiMix v2 13B

How much VRAM does UndiMix v2 13B need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 UndiMix v2 13B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of UndiMix v2 13B GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 6 more.

What context length does UndiMix v2 13B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download UndiMix v2 13B GGUF?

The files are on Hugging Face in the TheBloke/UndiMix-v2-13B-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 UndiMix v2 13B 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.

Can I run UndiMix v2 13B on 8 GB VRAM?

Only the Q2_K quantisation (5.43 GB file) can run with about 12.6 GB VRAM, so 8 GB VRAM is insufficient.

Is this model suitable for commercial use?

No, the cc‑by‑nc‑4.0 license prohibits commercial use.

Does the model support image input?

No, the model has no vision capabilities.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Undimix models

All Undimix →

Other medium models

All medium models →