RO

rocket 3B

RocketGGUF by TheBlokeUpdated 2023-11-23
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant1.2 GB
Quick answer

rocket 3B needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.2 GB (Q2_K) to 3.0 GB (Q8_0).

Rocket 3B – a 2.8B parameter chat model in GGUF format

Rocket 3B is a 2.8B parameter GPT‑like model fine‑tuned with Direct Preference Optimization. It uses the ChatML prompt format and is released under a CC‑BY‑SA‑4.0 license. The model is available in multiple GGUF quantisations for efficient inference.

Good at

  • Chat‑style conversations
  • Reasoning within 4096‑token context
  • English‑centric content

Limits

  • No vision or multimodal support
  • Requires GPU for optimal performance
  • License requires attribution

Best for

  • Local chat assistants
  • Rapid prototyping of LLM apps
  • Educational demos

Who it’s for. Developers and researchers who need a compact, open‑source chat model that can run on modest hardware. The model is suitable for building local chat interfaces or testing new inference pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 3.0 GB
Fits Get file →
Q3_K_S1.3 GB 3.1 GB
Fits Get file →
Q3_K_M1.4 GB 3.2 GB
Fits Get file →
Q3_K_L1.5 GB 3.4 GB
Fits Get file →
Q4_01.6 GB 3.5 GB
Fits Get file →
Q4_K_S1.6 GB 3.5 GB
Fits Get file →
Q4_K_M1.7 GB 3.6 GB
Fits Get file →
Q5_01.9 GB 3.8 GB
Fits Get file →
Q5_K_S1.9 GB 3.8 GB
Fits Get file →
Q5_K_M2.0 GB 3.8 GB
Fits Get file →
Q6_K2.3 GB 4.1 GB
Fits Get file →
Q8_03.0 GB 4.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.71 GB file, ~4.9 GB VRAM at 8k context). If 6 GB VRAM is available, Q3_K_M (1.39 GB file, ~4.6 GB VRAM) is a good balance. For 4 GB VRAM, Q2_K (1.2 GB file, ~4.4 GB VRAM) is the lightest option. Estimates are approximate.

What GPU do you need for rocket 3B?

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 Q6_K (2.3 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.2 GB in use).

Which rocket 3B quant should you choose?

Q4_K_M is the usual starting point for rocket 3B: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 3.0 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 1.2 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

Architecturestablelm
Parameters2.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyRocket
Downloads (HF)3,699
Last updated2023-11-23

Frequently asked questions about rocket 3B

How much VRAM does rocket 3B need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 rocket 3B on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rocket 3B GGUF?

It depends on the quant: Q2_K is 1.2 GB, Q3_K_S is 1.3 GB, Q3_K_M is 1.4 GB, Q3_K_L is 1.5 GB, Q4_0 is 1.6 GB, Q4_K_S is 1.6 GB and 6 more.

What context length does rocket 3B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download rocket 3B GGUF?

The files are on Hugging Face in the TheBloke/rocket-3B-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 rocket 3B use?

Hugging Face lists the license as cc-by-sa-4.0. 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 Rocket 3B on 8 GB VRAM?

Yes, a Q4_K_M quantised model (~1.71 GB file) will use about 4.9 GB VRAM at 8k context, leaving headroom for other processes.

Does Rocket 3B support image inputs?

No, the model only handles text and does not have vision capabilities.

Other GGUFs of rocket-3B

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Rocket models

All Rocket →

Other tiny models

All tiny models →