OP

openbuddy-zen-3b-v21.2-32k

OpenbuddyGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters4.77B
Context32K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

openbuddy-zen-3b-v21.2-32k needs about 4.5 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 2.0 GB (Q2_K) to 9.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

OpenBuddy Zen 3B with 32k context, 4.77B parameters

OpenBuddy Zen 3B is a 4.77B parameter Llama‑based model fine‑tuned on English and Chinese. It supports a 32,768 token context window and is distributed in multiple GGUF quantizations. The model is licensed under an other license and has no vision capabilities.

Good at

  • Large context handling
  • Multilingual English/Chinese
  • Fine‑tuned Llama3 architecture

Limits

  • No vision support
  • License not specified for commercial use
  • Requires GGUF quant files

Best for

  • Chatbots needing long context
  • Research prototypes
  • Low‑latency inference on GPU

Who it’s for. Developers building multilingual chat applications or research projects that require a 32k token window. The model is suitable for those who can manage the provided GGUF files and comply with the license terms.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.0 GB 3.6 GB
Fits Get file →
IQ3_XS2.2 GB 3.8 GB
Fits Get file →
Q3_K_S2.3 GB 3.8 GB
Fits Get file →
IQ3_S2.3 GB 3.9 GB
Fits Get file →
IQ3_M2.4 GB 4.0 GB
Fits Get file →
Q3_K_M2.5 GB 4.0 GB
Fits Get file →
Q3_K_L2.6 GB 4.2 GB
Fits Get file →
IQ4_XS2.7 GB 4.3 GB
Fits Get file →
Q4_K_S2.8 GB 4.4 GB
Fits Get file →
Q4_K_M3.0 GB 4.5 GB
Fits Get file →
Q5_K_S3.4 GB 4.9 GB
Fits Get file →
Q5_K_M3.4 GB 5.0 GB
Fits Get file →
Q6_K3.9 GB 5.5 GB
Fits Get file →
Q8_05.1 GB 6.6 GB
Fits Get file →
F169.5 GB 11.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 2.95 GB, estimated 4.5 GB memory). For 12 GB VRAM use Q5_K_M (3.42 GB, 5 GB memory). For 16 GB VRAM use Q6_K (3.92 GB, 5.5 GB memory). All estimates are approximate.

What GPU do you need for openbuddy-zen-3b-v21.2-32k?

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: the best quant that fits is Q3_K_M (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.9 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.1 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (9.5 GB file, about 11.1 GB in use).

Which openbuddy-zen-3b-v21.2-32k quant should you choose?

Q4_K_M is the usual starting point for openbuddy-zen-3b-v21.2-32k: it balances file size and quality well. Here it is a 3.0 GB file.

The Q8_0 file is 5.1 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 2.0 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
Parameters4.77B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyOpenbuddy
Licenseother
Downloads (HF)532
Last updated2024-12-16

Frequently asked questions about openbuddy-zen-3b-v21.2-32k

How much VRAM does openbuddy-zen-3b-v21.2-32k need?

About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.0 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 openbuddy-zen-3b-v21.2-32k on an 8 GB GPU?

Yes, with Q8_0: the 5.1 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of openbuddy-zen-3b-v21.2-32k GGUF?

It depends on the quant: Q2_K is 2.0 GB, IQ3_XS is 2.2 GB, Q3_K_S is 2.3 GB, IQ3_S is 2.3 GB, IQ3_M is 2.4 GB, Q3_K_M is 2.5 GB and 9 more.

What context length does openbuddy-zen-3b-v21.2-32k support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download openbuddy-zen-3b-v21.2-32k GGUF?

The files are on Hugging Face in the mradermacher/openbuddy-zen-3b-v21.2-32k-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-zen-3b-v21.2-32k 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 OpenBuddy Zen 3B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 4.5 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support vision?

No, the model has no vision capabilities.

What languages does it support?

It is designed for English and Chinese.

Other GGUFs of openbuddy-zero-3b-v21.2-32k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Openbuddy models

All Openbuddy →

Other small models

All small models →