GP

GPT_neo_Custom_14B_clean

GptGGUF by Szymon-WachelkoUpdated 2026-10-13
Download on Hugging Face
Parameters14.1B
Context32K
Layers56
Architectureqwen2
Smallest quant5.4 GB
Quick answer

GPT_neo_Custom_14B_clean needs about 10.0 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.4 GB (Q2_K) to 28.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

GPT‑neo‑Custom 14B‑DUS: Polish‑English conversational LLM with 14.1B parameters

GPT‑neo‑Custom 14B‑DUS is a conversational language model built on the Qwen2 architecture and Depth Up‑Scaling. It offers deep reasoning, coding proficiency, and native Polish fluency. The model is available in multiple GGUF quantizations for local deployment.

Good at

  • Polish language generation
  • Coding in multiple languages
  • Chain‑of‑thought reasoning

Limits

  • No vision support
  • Requires 8k context for full performance
  • Apache‑2.0 license

Best for

  • Local coding assistants
  • Polish‑English translation tasks
  • Educational tutoring

Who it’s for. Developers and researchers needing a high‑capacity Polish‑English LLM that can run on local hardware. The model is suitable for applications that require deep reasoning and code generation without cloud dependencies.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 6.8 GB
Fits Get file →
Q3_K_S6.3 GB 7.7 GB
Tight Get file →
Q3_K_M6.9 GB 8.4 GB
Too big Get file →
Q3_K_L7.5 GB 8.9 GB
Too big Get file →
Q4_K_S8.2 GB 9.6 GB
Too big Get file →
Q4_K_M8.6 GB 10.0 GB
Too big Get file →
Q5_K_S9.8 GB 11.2 GB
Too big Get file →
Q5_K_M10.1 GB 11.5 GB
Too big Get file →
Q6_K11.6 GB 13.0 GB
Too big Get file →
Q8_015.0 GB 16.5 GB
Too big Get file →
F1628.3 GB 29.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 8.61 GB, estimated 10 GB memory). For 12 GB VRAM, Q5_K_M (10.06 GB, 11.5 GB memory) is appropriate. If more memory is available, Q8_0 (15.03 GB, 16.5 GB memory) provides higher precision.

What GPU do you need for GPT_neo_Custom_14B_clean?

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: the best quant that fits is Q3_K_S (6.3 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (10.1 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.6 GB file, about 13.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.0 GB file, about 16.5 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (28.3 GB file, about 29.7 GB in use).

Which GPT_neo_Custom_14B_clean quant should you choose?

Q4_K_M is the usual starting point for GPT_neo_Custom_14B_clean: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 15.0 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 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

Architectureqwen2
Parameters14.1B
Layers56
Trained context32,768 tokens
KV cache (fp16)112 KB per token

Source

Quantized bySzymon-Wachelko
FamilyGpt
Licenseapache-2.0
Downloads (HF)497
Last updated2026-10-13

Frequently asked questions about GPT_neo_Custom_14B_clean

How much VRAM does GPT_neo_Custom_14B_clean need?

About 10.0 GB at Q4_K_M with an 8K context window. That is the 8.6 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 GPT_neo_Custom_14B_clean on an 8 GB GPU?

Yes, with Q3_K_S: the 6.3 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GPT_neo_Custom_14B_clean GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 6.3 GB, Q3_K_M is 6.9 GB, Q3_K_L is 7.5 GB, Q4_K_S is 8.2 GB, Q4_K_M is 8.6 GB and 5 more.

What context length does GPT_neo_Custom_14B_clean support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download GPT_neo_Custom_14B_clean GGUF?

The files are on Hugging Face in the Szymon-Wachelko/GPT-neo-Custom-14B-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 GPT_neo_Custom_14B_clean 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 GPT‑neo‑Custom 14B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 10 GB of VRAM at 8k context, which fits within an 8 GB GPU with some headroom.

Does the model support image input?

No, the model has no vision capabilities and only processes text.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from Szymon-Wachelko

All by Szymon-Wachelko →

More Gpt models

All Gpt →

Other medium models

All medium models →