ZH

Zhigong 1.6B Base

ZhigongGGUF by mradermacherUpdated 2024-09-12
Download on Hugging Face
Parameters1.66B
Context8K
Layers24
Architecturellama
Smallest quant0.7 GB
Quick answer

Zhigong 1.6B Base needs about 3.1 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.7 GB (Q2_K) to 3.3 GB (F16).

Zhigong 1.6B Base – a compact Llama‑style model

Zhigong 1.6B Base is a 1.66 B parameter Llama architecture model. It supports a 8192 token context window and is available in multiple GGUF quantizations. The model is provided by mradermacher and has no special license restrictions.

Good at

  • Fast inference on modest GPUs
  • Low memory footprint with Q2_K
  • Good balance of speed and quality

Limits

  • No vision support
  • No license information
  • Limited to 8192 token context

Best for

  • Chatbots on edge devices
  • Rapid prototyping of LLM apps
  • Educational demonstrations

Who it’s for. Developers and hobbyists who need a small, efficient Llama model for local inference. The model is suitable for those who prefer open-source tooling such as llama.cpp and want to experiment with different quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 2.8 GB
Fits Get file →
IQ3_XS0.8 GB 2.9 GB
Fits Get file →
IQ3_S0.8 GB 2.9 GB
Fits Get file →
Q3_K_S0.8 GB 2.9 GB
Fits Get file →
IQ3_M0.8 GB 2.9 GB
Fits Get file →
Q3_K_M0.9 GB 3.0 GB
Fits Get file →
Q3_K_L0.9 GB 3.0 GB
Fits Get file →
IQ4_XS0.9 GB 3.1 GB
Fits Get file →
Q4_K_S1.0 GB 3.1 GB
Fits Get file →
Q4_K_M1.0 GB 3.1 GB
Fits Get file →
Q5_K_S1.2 GB 3.3 GB
Fits Get file →
Q5_K_M1.2 GB 3.3 GB
Fits Get file →
Q6_K1.4 GB 3.5 GB
Fits Get file →
Q8_01.8 GB 3.9 GB
Fits Get file →
F163.3 GB 5.4 GB
Fits Get file →

For 8 GB VRAM use Q2_K (0.7 GB, 2.8 GB memory) or IQ3_XS (0.77 GB, 2.9 GB memory). If 12 GB VRAM is available, Q4_K_M (1.04 GB, 3.1 GB memory) offers better quality. For 16 GB VRAM, Q5_K_M (1.19 GB, 3.3 GB memory) or Q6_K (1.36 GB, 3.5 GB memory) are recommended.

What GPU do you need for Zhigong 1.6B Base?

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 Q8_0 (1.8 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.3 GB file, about 5.4 GB in use).

Which Zhigong 1.6B Base quant should you choose?

Q4_K_M is the usual starting point for Zhigong 1.6B Base: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 1.8 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 0.7 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
Parameters1.66B
Layers24
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyZhigong
Downloads (HF)819
Last updated2024-09-12

Frequently asked questions about Zhigong 1.6B Base

How much VRAM does Zhigong 1.6B Base need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Zhigong 1.6B Base on an 8 GB GPU?

Yes, with F16: the 3.3 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Zhigong 1.6B Base GGUF?

It depends on the quant: Q2_K is 0.7 GB, IQ3_XS is 0.8 GB, IQ3_S is 0.8 GB, Q3_K_S is 0.8 GB, IQ3_M is 0.8 GB, Q3_K_M is 0.9 GB and 9 more.

What context length does Zhigong 1.6B Base support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download Zhigong 1.6B Base GGUF?

The files are on Hugging Face in the mradermacher/Zhigong-1.6B-Base-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Zhigong 1.6B Base on 8 GB VRAM?

Yes, use Q2_K or IQ3_XS; both fit within 8 GB VRAM with estimated memory usage below 3 GB.

Does the model support vision tasks?

No, the model has no vision capabilities.

What context length does the model support?

The model supports a maximum context length of 8192 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Zhigong models

All Zhigong →

Other tiny models

All tiny models →