OP

openbuddy-zero-14b-v22.3-32k

OpenbuddyGGUF by mradermacherUpdated 2024-07-19
Download on Hugging Face
Parameters14B
Context32K
Layers78
Architecturellama
Smallest quant5.3 GB
Quick answer

openbuddy-zero-14b-v22.3-32k needs about 10.2 GB of memory at Q4_K_M (a 8.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.3 GB (Q2_K) to 14.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.2 GB.

14B OpenBuddy model with 32K context

OpenBuddy zero 14B v22.3 supports 32K context tokens and multilingual chat. It is based on llama architecture and includes weights from Yi-1.5-9B-32K and DeepSeek-VL-7B-chat. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Multilingual dialogue
  • Low‑memory inference

Limits

  • No vision support
  • License is other
  • No official benchmark scores

Best for

  • Chatbots with long conversations
  • Research on multilingual LLMs
  • Deploying on limited GPU memory

Who it’s for. Developers and researchers needing a 14B llama model with 32K context for chat or research. The model is suitable for environments where GPU memory is constrained and a variety of quantizations are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.3 GB 7.1 GB
Fits Get file →
IQ3_XS5.8 GB 7.6 GB
Tight Get file →
Q3_K_S6.1 GB 7.9 GB
Tight Get file →
IQ3_S6.2 GB 8.0 GB
Tight Get file →
IQ3_M6.4 GB 8.2 GB
Too big Get file →
Q3_K_M6.8 GB 8.6 GB
Too big Get file →
Q3_K_L7.4 GB 9.2 GB
Too big Get file →
IQ4_XS7.6 GB 9.4 GB
Too big Get file →
Q4_K_S8.0 GB 9.8 GB
Too big Get file →
Q4_K_M8.4 GB 10.2 GB
Too big Get file →
Q5_K_S9.7 GB 11.5 GB
Too big Get file →
Q5_K_M9.9 GB 11.7 GB
Too big Get file →
Q6_K11.5 GB 13.3 GB
Too big Get file →
Q8_014.9 GB 16.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 8.42 GB, estimated 10.2 GB memory). For 12 GB VRAM, Q5_K_M (9.92 GB, 11.7 GB memory) is a good balance. For 16 GB VRAM, Q6_K (11.51 GB, 13.3 GB memory) or Q8_0 (14.9 GB, 16.7 GB memory) can be used.

What GPU do you need for openbuddy-zero-14b-v22.3-32k?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_S (6.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.9 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.5 GB file, about 13.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.9 GB file, about 16.7 GB in use).

Which openbuddy-zero-14b-v22.3-32k quant should you choose?

Q4_K_M is the usual starting point for openbuddy-zero-14b-v22.3-32k: it balances file size and quality well. Here it is a 8.4 GB file.

The Q8_0 file is 14.9 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 5.3 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
Parameters14B
Layers78
Trained context32,768 tokens
KV cache (fp16)156 KB per token

Source

Quantized bymradermacher
FamilyOpenbuddy
Licenseother
Downloads (HF)1,763
Last updated2024-07-19

Frequently asked questions about openbuddy-zero-14b-v22.3-32k

How much VRAM does openbuddy-zero-14b-v22.3-32k need?

About 10.2 GB at Q4_K_M with an 8K context window. That is the 8.4 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 openbuddy-zero-14b-v22.3-32k on an 8 GB GPU?

Yes, with IQ3_S: the 6.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of openbuddy-zero-14b-v22.3-32k GGUF?

It depends on the quant: Q2_K is 5.3 GB, IQ3_XS is 5.8 GB, Q3_K_S is 6.1 GB, IQ3_S is 6.2 GB, IQ3_M is 6.4 GB, Q3_K_M is 6.8 GB and 8 more.

What context length does openbuddy-zero-14b-v22.3-32k support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.2 GB at 32K.

Where can I download openbuddy-zero-14b-v22.3-32k GGUF?

The files are on Hugging Face in the mradermacher/openbuddy-zero-14b-v22.3-32k-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 openbuddy-zero-14b-v22.3-32k use?

Hugging Face lists the license as other. 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 this model on 8 GB VRAM?

Yes, use Q4_K_M which requires about 10.2 GB memory at 8K context, which is close to 8 GB but may need swapping.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under an other license, not Apache 2.0 or DeepSeek.

Other GGUFs of openbuddy-zero-14b-v22.3-32k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Openbuddy models

All Openbuddy →

Other medium models

All medium models →