QW

14B Qwen2.5 Freya x1

QwenGGUF by bartowskiUpdated 2025-01-03
Download on Hugging Face
Parameters14.8B
Context32K
Layers48
Architectureqwen2
Smallest quant5.0 GB
Quick answer

14B Qwen2.5 Freya x1 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 24 quants, from 5.0 GB (IQ2_S) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

14B Qwen2.5 Freya x1 – a 14.8B parameter instruction model

The 14B Qwen2.5 Freya x1 model is a 14.8B parameter instruction‑tuned model based on Qwen2.5. It supports a 32768 token context window and is available in multiple GGUF quantizations. The model was trained with LoRA on literature and raw text.

Good at

  • Instruction following
  • Long context handling
  • Low‑memory inference

Limits

  • No vision support
  • License is other
  • Requires 8k context for memory estimates

Best for

  • Chatbot prototypes
  • Text summarization
  • Code generation

Who it’s for. Developers building lightweight LLM applications who need a large‑context model that can run on consumer GPUs. The model is suitable for users who can manage the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S5.0 GB 7.1 GB
Fits Get file →
IQ2_M5.4 GB 7.5 GB
Tight Get file →
Q2_K5.8 GB 7.9 GB
Tight Get file →
IQ3_XS6.4 GB 8.5 GB
Too big Get file →
Q2_K_L6.5 GB 8.6 GB
Too big Get file →
Q3_K_S6.7 GB 8.8 GB
Too big Get file →
IQ3_M6.9 GB 9.0 GB
Too big Get file →
Q3_K_M7.3 GB 9.4 GB
Too big Get file →
Q3_K_L7.9 GB 10.0 GB
Too big Get file →
IQ4_XS8.1 GB 10.2 GB
Too big Get file →
Q4_08.5 GB 10.7 GB
Too big Get file →
IQ4_NL8.5 GB 10.7 GB
Too big Get file →
Q4_K_S8.6 GB 10.7 GB
Too big Get file →
Q3_K_XL8.6 GB 10.7 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 GB
Too big Get file →
Q4_19.4 GB 11.5 GB
Too big Get file →
Q4_K_L9.6 GB 11.7 GB
Too big Get file →
Q5_K_S10.3 GB 12.4 GB
Too big Get file →
Q5_K_M10.5 GB 12.6 GB
Too big Get file →
Q5_K_L11.0 GB 13.1 GB
Too big Get file →
Q6_K12.1 GB 14.2 GB
Too big Get file →
Q6_K_L12.5 GB 14.6 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 →

For 8–12 GB VRAM, use Q4_0 (file size 8.54 GB, memory 10.7 GB) or Q4_K_S (8.57 GB, 10.7 GB). For 12–16 GB VRAM, Q5_K_M (10.51 GB, 12.6 GB) or Q6_K (12.12 GB, 14.2 GB) provide a balance of quality and memory. For 16 GB+ VRAM, Q8_0 (15.7 GB, 17.8 GB) gives the highest fidelity.

What GPU do you need for 14B Qwen2.5 Freya x1?

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 Q2_K (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_L (9.6 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_L (12.5 GB file, about 14.6 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 14B Qwen2.5 Freya x1 quant should you choose?

Q4_K_M is the usual starting point for 14B Qwen2.5 Freya x1: 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 IQ2_S at 5.0 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
Parameters14.8B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bybartowski
FamilyQwen
Licenseother
Downloads (HF)1,510
Last updated2025-01-03

Frequently asked questions about 14B Qwen2.5 Freya x1

How much VRAM does 14B Qwen2.5 Freya x1 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 14B Qwen2.5 Freya x1 on an 8 GB GPU?

Yes, with Q2_K: the 5.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of 14B Qwen2.5 Freya x1 GGUF?

It depends on the quant: IQ2_S is 5.0 GB, IQ2_M is 5.4 GB, Q2_K is 5.8 GB, IQ3_XS is 6.4 GB, Q2_K_L is 6.5 GB, Q3_K_S is 6.7 GB and 18 more.

What context length does 14B Qwen2.5 Freya x1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download 14B Qwen2.5 Freya x1 GGUF?

The files are on Hugging Face in the bartowski/14B-Qwen2.5-Freya-x1-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 14B Qwen2.5 Freya x1 use?

Hugging Face lists the license as other. 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?

With Q4_0 or Q4_K_S quantization, the model uses about 10.7 GB of VRAM at 8k context, so 8 GB is insufficient.

Does the model support image input?

No, the model has no vision capabilities.

What context length does it support?

It supports up to 32768 tokens, but memory estimates are for 8k context.

Other GGUFs of 14B-Qwen2.5-Freya-x1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Qwen models

All Qwen →

Other medium models

All medium models →