QW

Qwen2.5 14B Instruct Abliterated

QwenGGUF by mradermacherUpdated 2024-09-26
Download on Hugging Face
Parameters14.8B
Context32K
Layers48
Architectureqwen2
Smallest quant3.6 GB
Quick answer

Qwen2.5 14B Instruct Abliterated 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 3.6 GB (IQ1_S) to 12.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Qwen2.5 14B Instruct Abliterated – 14.8B parameter instruction model

Qwen2.5 14B Instruct Abliterated is a 14.8B parameter instruction-following model based on the Qwen2 architecture. It is available in multiple GGUF quantizations and licensed under apache-2.0. The model supports a 32768 token context window.

Good at

  • Instruction following
  • Large context handling
  • High parameter count

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache-2.0

Best for

  • Chatbots needing long context
  • Content generation with extended prompts
  • Fine‑tuning on custom instruction data

Who it’s for. Developers and researchers who need a large instruction‑tuned model with flexible quantization options. The model is suitable for local deployment via llama.cpp on systems with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.6 GB 5.7 GB
Fits Get file →
IQ1_M3.9 GB 6.0 GB
Fits Get file →
IQ2_XXS4.3 GB 6.4 GB
Fits Get file →
IQ2_XS4.7 GB 6.8 GB
Fits Get file →
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_XXS5.9 GB 8.1 GB
Too big Get file →
IQ3_XS6.4 GB 8.5 GB
Too big Get file →
Q3_K_S6.7 GB 8.8 GB
Too big Get file →
IQ3_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 10.6 GB
Too big Get file →
Q4_08.5 GB 10.6 GB
Too big Get file →
Q4_08.5 GB 10.6 GB
Too big Get file →
Q4_08.5 GB 10.7 GB
Too big Get file →
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 →
Q5_K_M10.5 GB 12.6 GB
Too big Get file →
Q6_K12.1 GB 14.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (3.61 GB file, 5.7 GB memory) or IQ1_M (3.87 GB file, 6 GB memory). With 12‑GB VRAM, IQ2_M (5.36 GB file, 7.5 GB memory) or Q3_K_M (7.34 GB file, 9.4 GB memory) are suitable. For 16‑GB VRAM, Q5_K_M (10.51 GB file, 12.6 GB memory) or Q6_K (12.12 GB file, 14.2 GB memory) provide higher quality.

What GPU do you need for Qwen2.5 14B Instruct Abliterated?

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: the best quant that fits is IQ1_M (3.9 GB file, about 6.0 GB in use).
  • 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_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).

Which Qwen2.5 14B Instruct Abliterated quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 14B Instruct Abliterated: it balances file size and quality well. Here it is a 9.0 GB file.

If memory is tight, the smallest file is IQ1_S at 3.6 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

Architectureqwen2
Parameters14.8B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,893
Last updated2024-09-26

Frequently asked questions about Qwen2.5 14B Instruct Abliterated

How much VRAM does Qwen2.5 14B Instruct Abliterated 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 Qwen2.5 14B Instruct Abliterated 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 Qwen2.5 14B Instruct Abliterated GGUF?

It depends on the quant: IQ1_S is 3.6 GB, IQ1_M is 3.9 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 5.0 GB, IQ2_M is 5.4 GB and 18 more.

What context length does Qwen2.5 14B Instruct Abliterated 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 Qwen2.5 14B Instruct Abliterated GGUF?

The files are on Hugging Face in the mradermacher/Qwen2.5-14B-Instruct-abliterated-i1-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 Qwen2.5 14B Instruct Abliterated 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 Qwen2.5 14B Instruct Abliterated on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations which require about 5.7–6 GB memory at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →