MI

MiniLoong-3B

MiniloongGGUF by mradermacherUpdated 2024-07-09
Download on Hugging Face
Parameters3.02B
Context31K
Layers24
Architecturellama
Smallest quant1.2 GB
Quick answer

MiniLoong-3B needs about 4.8 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.2 GB (Q2_K) to 6.0 GB (F16).

MiniLoong-3B – 3.02B parameter LLaMA‑style model

MiniLoong-3B is a 3.02B parameter LLaMA‑based model trained on 32,000 token context. It is released under apache‑2.0 and available in multiple GGUF quantizations. The model supports only text generation.

Good at

  • Text generation
  • Prompt completion
  • Language modeling

Limits

  • No vision support
  • Requires 8,000 token context for estimates
  • License requires LLaMA‑2 compliance

Best for

  • Chatbot prototypes
  • Text summarization
  • Code generation

Who it’s for. Developers building lightweight LLM applications who need a small, open‑source model. The model is suitable for local inference on consumer hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 4.1 GB
Fits Get file →
IQ3_XS1.3 GB 4.2 GB
Fits Get file →
IQ3_S1.4 GB 4.3 GB
Fits Get file →
Q3_K_S1.4 GB 4.3 GB
Fits Get file →
IQ3_M1.4 GB 4.3 GB
Fits Get file →
Q3_K_M1.5 GB 4.4 GB
Fits Get file →
Q3_K_L1.6 GB 4.5 GB
Fits Get file →
IQ4_XS1.7 GB 4.6 GB
Fits Get file →
Q4_K_S1.8 GB 4.7 GB
Fits Get file →
Q4_K_M1.8 GB 4.8 GB
Fits Get file →
Q5_K_S2.1 GB 5.0 GB
Fits Get file →
Q5_K_M2.2 GB 5.1 GB
Fits Get file →
Q6_K2.5 GB 5.4 GB
Fits Get file →
Q8_03.2 GB 6.1 GB
Fits Get file →
F166.0 GB 9.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (1.85 GB file, ~4.8 GB memory). For 12 GB VRAM, Q5_K_M (2.15 GB file, ~5.1 GB memory). For 16 GB VRAM, Q6_K (2.48 GB file, ~5.4 GB memory).

What GPU do you need for MiniLoong-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 (2.5 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (6.0 GB file, about 9.0 GB in use).

Which MiniLoong-3B quant should you choose?

Q4_K_M is the usual starting point for MiniLoong-3B: it balances file size and quality well. Here it is a 1.8 GB file.

The Q8_0 file is 3.2 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

Architecturellama
Parameters3.02B
Layers24
Trained context32,000 tokens
KV cache (fp16)288 KB per token

Source

Quantized bymradermacher
FamilyMiniloong
Licenseapache-2.0
Downloads (HF)1,587
Last updated2024-07-09

Frequently asked questions about MiniLoong-3B

How much VRAM does MiniLoong-3B need?

About 4.8 GB at Q4_K_M with an 8K context window. That is the 1.8 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 MiniLoong-3B on an 8 GB GPU?

Yes, with Q8_0: the 3.2 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniLoong-3B GGUF?

It depends on the quant: Q2_K is 1.2 GB, IQ3_XS is 1.3 GB, IQ3_S is 1.4 GB, Q3_K_S is 1.4 GB, IQ3_M is 1.4 GB, Q3_K_M is 1.5 GB and 9 more.

What context length does MiniLoong-3B support?

The GGUF header lists a trained context length of 32,000 tokens (31K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.4 GB at 31K.

Where can I download MiniLoong-3B GGUF?

The files are on Hugging Face in the mradermacher/MiniLoong-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 MiniLoong-3B use?

Hugging Face lists the license as apache-2.0. 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 MiniLoong-3B on 8 GB VRAM?

Yes, using Q4_K_M quantization requires about 4.8 GB VRAM at 8,000 token context.

Does MiniLoong-3B support image inputs?

No, the model only handles text and has no vision capabilities.

What license applies to MiniLoong-3B?

The model is distributed under apache‑2.0 and must comply with LLaMA‑2 license terms.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other tiny models

All tiny models →