NE

TQ2.5 14B Neon v1

NeonGGUF by allura-orgUpdated 2024-12-19
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant8.6 GB
Quick answer

TQ2.5 14B Neon v1 needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 8.6 GB (Q4_K_S) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

TQ2.5 14B Neon v1 is a 14.8B-parameter Neon model in GGUF format, quantized by allura-org. Its trained context length is 128K tokens. The repository has 6 quant files, from 8.6 GB (Q4_K_S) to 29.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S8.6 GB 10.7 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 GB
Too big Get file →
Q5_K_S10.3 GB 12.4 GB
Too big Get file →
Q6_K12.1 GB 14.2 GB
Too big Get file →
Q8_015.7 GB 17.8 GB
Too big Get file →
F1629.5 GB 31.7 GB
Too big Get file →

What GPU do you need for TQ2.5 14B Neon v1?

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 Q4_K_M (9.0 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.8 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (29.5 GB file, about 31.7 GB in use).

Which TQ2.5 14B Neon v1 quant should you choose?

Q4_K_M is the usual starting point for TQ2.5 14B Neon v1: it balances file size and quality well. Here it is a 9.0 GB file.

The Q8_0 file is 15.7 GB, about 1.7 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_K_S at 8.6 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

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized byallura-org
FamilyNeon
Licenseapache-2.0
Downloads (HF)113
Last updated2024-12-19

Frequently asked questions about TQ2.5 14B Neon v1

How much VRAM does TQ2.5 14B Neon v1 need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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 TQ2.5 14B Neon v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of TQ2.5 14B Neon v1 GGUF?

It depends on the quant: Q4_K_S is 8.6 GB, Q4_K_M is 9.0 GB, Q5_K_S is 10.3 GB, Q6_K is 12.1 GB, Q8_0 is 15.7 GB, F16 is 29.5 GB.

What context length does TQ2.5 14B Neon v1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download TQ2.5 14B Neon v1 GGUF?

The files are on Hugging Face in the allura-org/TQ2.5-14B-Neon-v1-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 TQ2.5 14B Neon v1 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.

Other GGUFs of TQ2.5-14B-Neon-v1

Similar models

Browse all →

More from allura-org

All by allura-org →

More Neon models

All Neon →

Other medium models

All medium models →