WI

WizardLM-2-7B-abliterated

WizardlmGGUF by bartowskiUpdated 2024-05-26
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

WizardLM-2-7B-abliterated needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 23 quants, from 1.6 GB (IQ1_S) to 29.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

WizardLM-2-7B-abliterated – 7.24B llama model in GGUF format

WizardLM-2-7B-abliterated is a 7.24B parameter llama architecture model. It supports a 32768 token context window and is released under apache-2.0. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Flexible quantization options
  • Apache-2.0 license

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Chat applications
  • Text generation tasks
  • Fine‑tuning on custom data

Who it’s for. Developers and researchers who need a large‑context LLM with flexible quantization. The model is suitable for deployment on GPUs with sufficient VRAM or on CPUs with enough RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.8 GB 3.3 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
IQ4_NL4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
F3229.0 GB 30.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.61 GB, 3.2 GB memory) or IQ1_M (1.75 GB, 3.3 GB memory). With 12 GB VRAM, IQ2_S (2.31 GB, 3.9 GB memory) or Q2_K (2.72 GB, 4.3 GB memory) are suitable. For 16 GB VRAM, IQ3_M (3.28 GB, 4.9 GB memory) or Q3_K_M (3.52 GB, 5.1 GB memory) provide a good balance of size and performance.

What GPU do you need for WizardLM-2-7B-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: the best quant that fits is IQ2_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 32 GB VRAM: the best quant that fits is F32 (29.0 GB file, about 30.5 GB in use).

Which WizardLM-2-7B-abliterated quant should you choose?

Q4_K_M is the usual starting point for WizardLM-2-7B-abliterated: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 IQ1_S at 1.6 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

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybartowski
FamilyWizardlm
Licenseapache-2.0
Downloads (HF)1,529
Last updated2024-05-26

Frequently asked questions about WizardLM-2-7B-abliterated

How much VRAM does WizardLM-2-7B-abliterated need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 WizardLM-2-7B-abliterated on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WizardLM-2-7B-abliterated GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 17 more.

What context length does WizardLM-2-7B-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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download WizardLM-2-7B-abliterated GGUF?

The files are on Hugging Face in the bartowski/WizardLM-2-7B-abliterated-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 WizardLM-2-7B-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 WizardLM-2-7B-abliterated on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations. They fit within 8 GB VRAM and use about 3.2–3.3 GB memory at 8k context.

What quantization gives the best quality?

Higher‑bit quants like Q5_K_S or Q5_K_M offer better quality but need more memory: 5 GB file size and 6.6–6.7 GB memory at 8k context.

Is the model licensed for commercial use?

The model is released under apache-2.0, which permits commercial use with attribution.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Wizardlm models

All Wizardlm →

Other small models

All small models →