CA

CantoneseLLMChat-v0.5

CantonesellmchatGGUF by mradermacherUpdated 2024-07-08
Download on Hugging Face
Parameters6.1B
Context4K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

CantoneseLLMChat-v0.5 needs about 4.7 GB of memory at Q4_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 2.3 GB (Q2_K) to 12.1 GB (F16).

6.1B Cantonese language model in GGUF format

CantoneseLLMChat‑v0.5 is a 6.1B parameter model fine‑tuned on Cantonese text. It supports chat‑style interactions with a default system prompt that encourages Cantonese responses. The model is released under the apache‑2.0 license.

Good at

  • Cantonese text generation
  • Chat‑style dialogue
  • Cantonese language understanding

Limits

  • Limited to Cantonese; not suitable for other Chinese varieties
  • May hallucinate or contain bias
  • Requires 8k context for full performance

Best for

  • Developing Cantonese chatbots
  • Generating Cantonese content
  • Research on Cantonese NLP

Who it’s for. Developers and researchers needing a Cantonese‑focused LLM. The model is suitable for applications that require Cantonese generation or understanding, but users should be aware of potential hallucinations and bias.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.3 GB 3.1 GB
Fits Get file →
IQ3_XS2.6 GB 3.4 GB
Fits Get file →
Q3_K_S2.7 GB 3.5 GB
Fits Get file →
IQ3_S2.7 GB 3.5 GB
Fits Get file →
IQ3_M2.8 GB 3.6 GB
Fits Get file →
Q3_K_M3.0 GB 3.8 GB
Fits Get file →
Q3_K_L3.2 GB 4.0 GB
Fits Get file →
IQ4_XS3.3 GB 4.1 GB
Fits Get file →
Q4_K_S3.5 GB 4.3 GB
Fits Get file →
Q4_K_M3.7 GB 4.4 GB
Fits Get file →
Q5_K_S4.2 GB 5.0 GB
Fits Get file →
Q5_K_M4.3 GB 5.1 GB
Fits Get file →
Q6_K5.0 GB 5.7 GB
Fits Get file →
Q8_06.5 GB 7.2 GB
Tight Get file →
F1612.1 GB 12.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 3.51 GB, memory 4.5 GB) or Q4_K_M (3.68 GB, 4.7 GB). For 12 GB VRAM, Q5_K_S (4.21 GB, 5.2 GB) or Q5_K_M (4.31 GB, 5.3 GB) are suitable. Higher‑precision quants like F16 (12.14 GB, 13.2 GB) require more memory but give better quality.

What GPU do you need for CantoneseLLMChat-v0.5?

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 Q3_K_M (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (5.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.5 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (6.5 GB file, about 7.5 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (12.1 GB file, about 13.2 GB in use).

Which CantoneseLLMChat-v0.5 quant should you choose?

Q4_K_M is the usual starting point for CantoneseLLMChat-v0.5: it balances file size and quality well. Here it is a 3.7 GB file.

The Q8_0 file is 6.5 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 Q2_K at 2.3 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
Parameters6.1B
Layers32
Trained context4,096 tokens
KV cache (fp16)64 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,472
Last updated2024-07-08

Frequently asked questions about CantoneseLLMChat-v0.5

How much VRAM does CantoneseLLMChat-v0.5 need?

About 4.7 GB at Q4_K_M with an 8K context window. That is the 3.7 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 CantoneseLLMChat-v0.5 on an 8 GB GPU?

Yes, with Q8_0: the 6.5 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 CantoneseLLMChat-v0.5 GGUF?

It depends on the quant: Q2_K is 2.3 GB, IQ3_XS is 2.6 GB, Q3_K_S is 2.7 GB, IQ3_S is 2.7 GB, IQ3_M is 2.8 GB, Q3_K_M is 3.0 GB and 9 more.

What context length does CantoneseLLMChat-v0.5 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.3 GB at 4K.

Where can I download CantoneseLLMChat-v0.5 GGUF?

The files are on Hugging Face in the mradermacher/CantoneseLLMChat-v0.5-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 CantoneseLLMChat-v0.5 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 CantoneseLLMChat-v0.5 on 8 GB VRAM?

Yes, using Q4_K_S or Q4_K_M quantizations will fit within 8 GB VRAM with an estimated 4.5–4.7 GB usage.

Does the model support other Chinese dialects?

The model is specifically trained for Cantonese and may not perform well on other Chinese varieties.

Is the model free to use?

Yes, it is released under the apache‑2.0 license, allowing free use and modification.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Cantonesellmchat models

All Cantonesellmchat →

Other small models

All small models →