MA

MagpieLM 4B Chat v0.1

MagpielmGGUF by QuantFactoryUpdated 2024-09-20
Download on Hugging Face
Parameters4.51B
Context128K
Layers32
Architecturellama
Smallest quant1.8 GB
Quick answer

MagpieLM 4B Chat v0.1 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 14 quants, from 1.8 GB (Q2_K) to 4.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MagpieLM 4B Chat v0.1 – a fine‑tuned Llama‑3.1 aligned model

MagpieLM 4B Chat v0.1 is a 4.51B parameter Llama‑3.1 model fine‑tuned on Magpie‑Align datasets. It supports 131072 token context and is available in multiple GGUF quantizations. The model is aligned for chat and instruction following.

Good at

  • Chat and instruction following
  • English‑centric conversations
  • Fine‑tuned alignment

Limits

  • No vision support
  • English‑only focus
  • License requires NVIDIA Open Model License

Best for

  • Building lightweight chatbots
  • Running on 8‑GB VRAM with Q4_K quant
  • Local inference with llama.cpp

Who it’s for. Developers and researchers who need a small, chat‑ready Llama‑3.1 variant. The model is suitable for local deployment and experimentation with different quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.8 GB 3.4 GB
Fits Get file →
Q3_K_S2.1 GB 3.7 GB
Fits Get file →
Q3_K_M2.3 GB 3.9 GB
Fits Get file →
Q3_K_L2.5 GB 4.0 GB
Fits Get file →
Q4_02.6 GB 4.2 GB
Fits Get file →
Q4_K_S2.7 GB 4.2 GB
Fits Get file →
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q4_12.9 GB 4.5 GB
Fits Get file →
Q5_03.2 GB 4.7 GB
Fits Get file →
Q5_K_S3.2 GB 4.7 GB
Fits Get file →
Q5_K_M3.2 GB 4.8 GB
Fits Get file →
Q5_13.4 GB 5.0 GB
Fits Get file →
Q6_K3.7 GB 5.3 GB
Fits Get file →
Q8_04.8 GB 6.4 GB
Fits Get file →

For 8‑GB VRAM, Q4_K or Q4_K_S (2.65 GB or 2.66 GB) are suitable, using about 4.2 GB VRAM at 8k context. If 12‑GB VRAM is available, Q5_K_M (3.23 GB) or Q5_1 (3.42 GB) provide higher quality. Larger models like Q6_K or Q8_0 require 5.3 GB or 6.4 GB VRAM respectively.

What GPU do you need for MagpieLM 4B Chat v0.1?

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_L (2.5 GB file, about 4.0 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 Q8_0 (4.8 GB file, about 6.4 GB in use).

Which MagpieLM 4B Chat v0.1 quant should you choose?

Q4_K_M is the usual starting point for MagpieLM 4B Chat v0.1: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.8 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 1.8 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 byQuantFactory
FamilyMagpielm
Licenseother
Downloads (HF)1,689
Last updated2024-09-20

Frequently asked questions about MagpieLM 4B Chat v0.1

How much VRAM does MagpieLM 4B Chat v0.1 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 MagpieLM 4B Chat v0.1 on an 8 GB GPU?

Yes, with Q8_0: the 4.8 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MagpieLM 4B Chat v0.1 GGUF?

It depends on the quant: Q2_K is 1.8 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.5 GB, Q4_0 is 2.6 GB, Q4_K_S is 2.7 GB and 8 more.

What context length does MagpieLM 4B Chat v0.1 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 MagpieLM 4B Chat v0.1 GGUF?

The files are on Hugging Face in the QuantFactory/MagpieLM-4B-Chat-v0.1-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 MagpieLM 4B Chat v0.1 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 MagpieLM 4B Chat on 8 GB VRAM?

Yes, use Q4_K or Q4_K_S quantizations; they use about 4.2 GB VRAM at 8k context.

Does the model support vision inputs?

No, the model only handles text.

What license applies to this model?

It requires following the NVIDIA Open Model License Agreement.

Other GGUFs of MagpieLM-4B-SFT-v0.1

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Magpielm models

All Magpielm →

Other small models

All small models →