HU

Hubble 4B V1C

HubbleGGUF by TheDrummerUpdated 2024-08-31
Download on Hugging Face
Parameters4.51B
Context128K
Layers32
Architecturellama
Smallest quant1.8 GB
Quick answer

Hubble 4B V1C needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.8 GB (Q2_K) to 9.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Hubble 4B V1C – a 4.51B finetuned Llama 3.1 4B model

Hubble 4B V1C is a finetuned version of Nvidia's Llama 3.1 4B Minitron. It supports ChatML and text completion with a 131072 token context window. The model is available in multiple GGUF quantizations.

Good at

  • ChatML compatible
  • Large 131072 token context
  • Fine‑tuned for conversational use

Limits

  • No vision support
  • License type is other
  • No mixture of experts

Best for

  • Chatbot development
  • Text generation tasks
  • Fine‑tuning experiments

Who it’s for. Developers looking for a lightweight Llama 3.1 variant with a large context window. Suitable for local inference on systems with moderate VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.8 GB 3.4 GB
Fits Get file →
Q3_K_M2.3 GB 3.9 GB
Fits Get file →
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q5_K_M3.2 GB 4.8 GB
Fits Get file →
Q6_K3.7 GB 5.3 GB
Fits Get file →
BF169.0 GB 10.6 GB
Too big Get file →
F169.0 GB 10.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.78 GB file, 4.4 GB memory). For 12 GB VRAM, Q5_K_M (3.23 GB file, 4.8 GB memory) is a good balance. If more memory is available, BF16 or F16 (9.03 GB file, 10.6 GB memory) can be used for higher precision.

What GPU do you need for Hubble 4B V1C?

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 (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.7 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.7 GB file, about 5.3 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (9.0 GB file, about 10.6 GB in use).

Which Hubble 4B V1C quant should you choose?

Q4_K_M is the usual starting point for Hubble 4B V1C: it balances file size and quality well. Here it is a 2.8 GB file.

If memory is tight, the smallest file is Q2_K at 1.8 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
Parameters4.51B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTheDrummer
FamilyHubble
Licenseother
Downloads (HF)700
Last updated2024-08-31

Frequently asked questions about Hubble 4B V1C

How much VRAM does Hubble 4B V1C need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Hubble 4B V1C on an 8 GB GPU?

Yes, with Q6_K: the 3.7 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hubble 4B V1C GGUF?

It depends on the quant: Q2_K is 1.8 GB, Q3_K_M is 2.3 GB, Q4_K_M is 2.8 GB, Q5_K_M is 3.2 GB, Q6_K is 3.7 GB, BF16 is 9.0 GB and 1 more.

What context length does Hubble 4B V1C support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Hubble 4B V1C GGUF?

The files are on Hugging Face in the TheDrummer/Hubble-4B-v1-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 Hubble 4B V1C 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 Hubble 4B V1C on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 4.4 GB of VRAM at 8 k context, which fits within 8 GB.

Does Hubble 4B V1C support vision tasks?

No, the model does not include vision capabilities.

Similar models

Browse all →

More from TheDrummer

All by TheDrummer →

More Hubble models

All Hubble →

Other small models

All small models →