ME

Megrez 3B Instruct

MegrezGGUF by second-stateUpdated 2025-01-11
Download on Hugging Face
Parameters2.92B
Context32K
Layers32
Architecturellama
Smallest quant1.2 GB
Quick answer

Megrez 3B Instruct needs about 3.0 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 1.2 GB (Q2_K) to 5.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Megrez 3B Instruct is a 2.92B-parameter Megrez model in GGUF format, quantized by second-state. Its trained context length is 32K tokens. The repository has 13 quant files, from 1.2 GB (Q2_K) to 5.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 2.4 GB
Fits Get file →
Q3_K_S1.4 GB 2.6 GB
Fits Get file →
Q3_K_M1.5 GB 2.7 GB
Fits Get file →
Q3_K_L1.6 GB 2.8 GB
Fits Get file →
Q4_01.7 GB 2.9 GB
Fits Get file →
Q4_K_S1.7 GB 2.9 GB
Fits Get file →
Q4_K_M1.8 GB 3.0 GB
Fits Get file →
Q5_02.1 GB 3.2 GB
Fits Get file →
Q5_K_S2.1 GB 3.2 GB
Fits Get file →
Q5_K_M2.1 GB 3.3 GB
Fits Get file →
Q6_K2.4 GB 3.6 GB
Fits Get file →
Q8_03.1 GB 4.3 GB
Fits Get file →
F165.8 GB 7.0 GB
Fits Get file →

What GPU do you need for Megrez 3B Instruct?

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 Q6_K (2.4 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.1 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.8 GB file, about 7.0 GB in use).

Which Megrez 3B Instruct quant should you choose?

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

The Q8_0 file is 3.1 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
Parameters2.92B
Layers32
Trained context32,768 tokens
KV cache (fp16)80 KB per token

Source

Quantized bysecond-state
FamilyMegrez
Licenseapache-2.0
Downloads (HF)415
Last updated2025-01-11

Frequently asked questions about Megrez 3B Instruct

How much VRAM does Megrez 3B Instruct need?

About 3.0 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 Megrez 3B Instruct on an 8 GB GPU?

Yes, with F16: the 5.8 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Megrez 3B Instruct GGUF?

It depends on the quant: Q2_K is 1.2 GB, Q3_K_S is 1.4 GB, Q3_K_M is 1.5 GB, Q3_K_L is 1.6 GB, Q4_0 is 1.7 GB, Q4_K_S is 1.7 GB and 7 more.

What context length does Megrez 3B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Megrez 3B Instruct GGUF?

The files are on Hugging Face in the second-state/Megrez-3B-Instruct-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 Megrez 3B Instruct 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.

Other GGUFs of Megrez-3B-Instruct

Similar models

Browse all →

More from second-state

All by second-state →

More Megrez models

All Megrez →

Other tiny models

All tiny models →