MI

miniclaus qw1.5B UNAMGS

MiniclausGGUF by bartowskiUpdated 2024-11-15
Download on Hugging Face
Parameters1.78B
Context128K
Layers28
Architectureqwen2
Smallest quant0.7 GB
Quick answer

miniclaus qw1.5B UNAMGS needs about 1.9 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.7 GB (IQ2_M) to 3.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

MiniClaus QW1.5B UNAMGS – a small, 1.78B‑parameter Qwen2 model

MiniClaus QW1.5B UNAMGS is a 1.78B‑parameter Qwen2 model trained with Magpie‑Align/Magpie‑Pro‑MT‑300K‑v0.1. It uses MGS & UNA (MLP) techniques. The model supports a 131072‑token context window.

Good at

  • Short‑form dialogue
  • Quick code snippets
  • Lightweight inference

Limits

  • No vision support
  • License type unknown
  • Large memory for higher quants

Best for

  • Embedded devices
  • Rapid prototyping
  • Low‑cost inference

Who it’s for. Developers needing a compact Qwen2 model for quick experimentation or deployment on limited hardware. The model is suitable for applications that require a 131072‑token context but can tolerate the memory demands of higher‑quality quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M0.7 GB 1.4 GB
Fits Get file →
Q2_K0.8 GB 1.5 GB
Fits Get file →
IQ3_XS0.8 GB 1.6 GB
Fits Get file →
Q3_K_S0.9 GB 1.6 GB
Fits Get file →
IQ3_M0.9 GB 1.6 GB
Fits Get file →
Q3_K_M0.9 GB 1.7 GB
Fits Get file →
Q3_K_L1.0 GB 1.7 GB
Fits Get file →
Q2_K_L1.0 GB 1.7 GB
Fits Get file →
IQ4_XS1.0 GB 1.8 GB
Fits Get file →
Q4_01.1 GB 1.8 GB
Fits Get file →
Q4_01.1 GB 1.8 GB
Fits Get file →
Q4_01.1 GB 1.8 GB
Fits Get file →
Q4_01.1 GB 1.8 GB
Fits Get file →
Q4_K_S1.1 GB 1.8 GB
Fits Get file →
Q4_K_M1.1 GB 1.9 GB
Fits Get file →
Q3_K_XL1.2 GB 1.9 GB
Fits Get file →
Q5_K_S1.3 GB 2.0 GB
Fits Get file →
Q5_K_M1.3 GB 2.0 GB
Fits Get file →
Q4_K_L1.3 GB 2.0 GB
Fits Get file →
Q5_K_L1.4 GB 2.2 GB
Fits Get file →
Q6_K1.5 GB 2.2 GB
Fits Get file →
Q6_K_L1.6 GB 2.3 GB
Fits Get file →
Q8_01.9 GB 2.6 GB
Fits Get file →
F163.6 GB 4.3 GB
Fits Get file →

For 8 GB VRAM, use IQ2_M (0.7 GB) or Q2_K (0.75 GB). If 12 GB VRAM is available, Q4_K_M (1.12 GB) or Q5_K_S (1.26 GB) provide better quality. For 16 GB VRAM, Q6_K (1.46 GB) or Q8_0 (1.89 GB) are options, with F16 (3.56 GB) requiring 4.3 GB memory at 8 k context.

What GPU do you need for miniclaus qw1.5B UNAMGS?

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 Q8_0 (1.9 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.6 GB file, about 4.3 GB in use).

Which miniclaus qw1.5B UNAMGS quant should you choose?

Q4_K_M is the usual starting point for miniclaus qw1.5B UNAMGS: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.9 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 IQ2_M at 0.7 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

Architectureqwen2
Parameters1.78B
Layers28
Trained context131,072 tokens
KV cache (fp16)28 KB per token

Source

Quantized bybartowski
FamilyMiniclaus
Licenseother
Downloads (HF)1,372
Last updated2024-11-15

Frequently asked questions about miniclaus qw1.5B UNAMGS

How much VRAM does miniclaus qw1.5B UNAMGS need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.1 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 miniclaus qw1.5B UNAMGS on an 8 GB GPU?

Yes, with F16: the 3.6 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of miniclaus qw1.5B UNAMGS GGUF?

It depends on the quant: IQ2_M is 0.7 GB, Q2_K is 0.8 GB, IQ3_XS is 0.8 GB, Q3_K_S is 0.9 GB, IQ3_M is 0.9 GB, Q3_K_M is 0.9 GB and 18 more.

What context length does miniclaus qw1.5B UNAMGS support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download miniclaus qw1.5B UNAMGS GGUF?

The files are on Hugging Face in the bartowski/miniclaus-qw1.5B-UNAMGS-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 miniclaus qw1.5B UNAMGS 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, using IQ2_M or Q2_K quants, which require about 1.4–1.5 GB memory at 8 k context.

Does this model support image input?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports a 131072‑token context window.

Other GGUFs of miniclaus-qw1.5B-UNAMGS

Similar models

Browse all →

More from bartowski

All by bartowski →

More Miniclaus models

All Miniclaus →

Other tiny models

All tiny models →