bartowski/CodeQwen1.5-7B-GGUF

---

license: other license_name: tongyi-qianwen-research license_link: >- https://huggingface.co/Qwen/CodeQwen1.5-7B/blob/main/LICENSE language:

• en

pipeline_tag: text-generation tags:

• pretrained

quantized_by: bartowski

---

Llamacpp Quantizations of CodeQwen1.5-7B

Using llama.cpp PR 6707 for quantization.

Original model: https://huggingface.co/Qwen/CodeQwen1.5-7B

All quants made using imatrix option with dataset provided by Kalomaze here

Prompt format

<|im_start|>system
{systemprompt}<|imend|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Description
CodeQwen1.5-7B-Q80.gguf	Q80	7.70GB	Extremely high quality, generally unneeded but max available quant.
CodeQwen1.5-7B-Q6K.gguf	Q6K	6.37GB	Very high quality, near perfect, recommended.
CodeQwen1.5-7B-Q5KM.gguf	Q5K_M	5.42GB	High quality, recommended.
CodeQwen1.5-7B-Q5KS.gguf	Q5K_S	5.14GB	High quality, recommended.
CodeQwen1.5-7B-Q4KM.gguf	Q4K_M	4.73GB	Good quality, uses about 4.83 bits per weight, recommended.
CodeQwen1.5-7B-Q4KS.gguf	Q4K_S	4.41GB	Slightly lower quality with more space savings, recommended.
CodeQwen1.5-7B-IQ4NL.gguf	IQ4NL	4.18GB	Decent quality, slightly smaller than Q4KS with similar performance recommended.
CodeQwen1.5-7B-IQ4XS.gguf	IQ4XS	4.03GB	Decent quality, smaller than Q4KS with similar performance, recommended.
CodeQwen1.5-7B-Q3KL.gguf	Q3K_L	3.98GB	Lower quality but usable, good for low RAM availability.
CodeQwen1.5-7B-Q3KM.gguf	Q3K_M	3.80GB	Even lower quality.
CodeQwen1.5-7B-IQ3M.gguf	IQ3M	3.60GB	Medium-low quality, new method with decent performance comparable to Q3KM.
CodeQwen1.5-7B-IQ3S.gguf	IQ3S	3.50GB	Lower quality, new method with decent performance, recommended over Q3KS quant, same size with better performance.
CodeQwen1.5-7B-Q3KS.gguf	Q3K_S	3.50GB	Low quality, not recommended.
CodeQwen1.5-7B-IQ3XS.gguf	IQ3XS	3.35GB	Lower quality, new method with decent performance, slightly better than Q3KS.
CodeQwen1.5-7B-IQ3XXS.gguf	IQ3XXS	3.22GB	Lower quality, new method with decent performance, comparable to Q3 quants.
CodeQwen1.5-7B-Q2K.gguf	Q2K	3.05GB	Very low quality but surprisingly usable.
CodeQwen1.5-7B-IQ2M.gguf	IQ2M	3.00GB	Very low quality, uses SOTA techniques to also be surprisingly usable.
CodeQwen1.5-7B-IQ2S.gguf	IQ2S	2.87GB	Very low quality, uses SOTA techniques to be usable.
CodeQwen1.5-7B-IQ2XS.gguf	IQ2XS	2.76GB	Very low quality, uses SOTA techniques to be usable.
CodeQwen1.5-7B-IQ2XXS.gguf	IQ2XXS	2.61GB	Lower quality, uses SOTA techniques to be usable.
CodeQwen1.5-7B-IQ1M.gguf	IQ1M	2.45GB	Extremely low quality, not recommended.
CodeQwen1.5-7B-IQ1S.gguf	IQ1S	2.36GB	Extremely low quality, not recommended.

Which file should I choose?

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QXKX', like Q5KM.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQXX, like IQ3M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski