CH

ChinaLM-9B

ChinalmGGUF by mradermacherUpdated 2024-06-18
Download on Hugging Face
Parameters8.93B
Context4K
Layers40
Architecturellama
Smallest quant3.5 GB
Quick answer

ChinaLM-9B needs about 6.6 GB of memory at Q4_K_M (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 3.5 GB (Q2_K) to 17.9 GB (F16).

ChinaLM-9B – 8.93B parameter Llama-based model in GGUF format

ChinaLM-9B is a 8.93 billion parameter Llama architecture model. It supports a 4096 token context window and is released under the MIT license. The model is available in multiple static quantizations.

Good at

  • Large language generation
  • Contextual understanding up to 4096 tokens
  • MIT licensed for free use

Limits

  • No vision support
  • No mixture of experts
  • Context limited to 4096 tokens

Best for

  • Chatbot back‑end
  • Text completion tasks
  • Research prototyping

Who it’s for. Developers and researchers needing a large language model that can be run locally with GGUF. The model is suitable for those who prefer open source licensing and static quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.5 GB 4.3 GB
Fits Get file →
IQ3_XS3.9 GB 4.7 GB
Fits Get file →
Q3_K_S4.1 GB 4.9 GB
Fits Get file →
IQ3_S4.1 GB 4.9 GB
Fits Get file →
IQ3_M4.2 GB 5.0 GB
Fits Get file →
Q3_K_M4.5 GB 5.3 GB
Fits Get file →
Q3_K_L4.8 GB 5.6 GB
Fits Get file →
IQ4_XS5.0 GB 5.8 GB
Fits Get file →
Q4_K_S5.2 GB 6.0 GB
Fits Get file →
Q4_K_M5.5 GB 6.3 GB
Fits Get file →
Q5_K_S6.2 GB 7.0 GB
Fits Get file →
Q5_K_M6.4 GB 7.2 GB
Tight Get file →
Q6_K7.3 GB 8.2 GB
Too big Get file →
Q8_09.5 GB 10.3 GB
Too big Get file →
F1617.9 GB 18.7 GB
Too big Get file →

For 8 GB VRAM, Q4_K_M (5.46 GB file, 6.6 GB memory at 8k context) is a good choice. If more VRAM is available, Q5_K_M (6.37 GB file, 7.5 GB memory) offers higher quality. For very limited memory, Q2_K (3.51 GB file, 4.7 GB memory) is the smallest option.

What GPU do you need for ChinaLM-9B?

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 Q3_K_L (4.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.4 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.9 GB file, about 19.0 GB in use).

Which ChinaLM-9B quant should you choose?

Q4_K_M is the usual starting point for ChinaLM-9B: it balances file size and quality well. Here it is a 5.5 GB file.

The Q8_0 file is 9.5 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 Q2_K at 3.5 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
Parameters8.93B
Layers40
Trained context4,096 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyChinalm
Licensemit
Downloads (HF)603
Last updated2024-06-18

Frequently asked questions about ChinaLM-9B

How much VRAM does ChinaLM-9B need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.5 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 ChinaLM-9B on an 8 GB GPU?

Yes, with Q5_K_M: the 6.4 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 ChinaLM-9B GGUF?

It depends on the quant: Q2_K is 3.5 GB, IQ3_XS is 3.9 GB, Q3_K_S is 4.1 GB, IQ3_S is 4.1 GB, IQ3_M is 4.2 GB, Q3_K_M is 4.5 GB and 9 more.

What context length does ChinaLM-9B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.3 GB at 4K.

Where can I download ChinaLM-9B GGUF?

The files are on Hugging Face in the mradermacher/ChinaLM-9B-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 ChinaLM-9B use?

Hugging Face lists the license as mit. 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 ChinaLM-9B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 6.6 GB of VRAM at 8k context, which fits within an 8 GB GPU.

What quantization gives the best quality?

Higher‑bit quantizations like Q5_K_M or Q6_K provide better quality, but need more memory.

Is the model licensed for commercial use?

The model is released under the MIT license, allowing commercial use with attribution.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other small models

All small models →