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 22 quants, from 1.1 GB (IQ2_M) to 5.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Megrez 3B Instruct – 2.92B‑parameter LLaMA‑style model with 32K context
Megrez 3B Instruct is a 2.92B‑parameter LLaMA‑based model trained by Infinigence AI. It supports 32K token context and is available in multiple GGUF quantizations. The model is licensed under Apache‑2.0 and is designed for easy deployment on a variety of platforms.
Good at
- High‑speed inference on small hardware
- 32K context for long‑form tasks
- WebSearch‑enabled dialogue
Limits
- No vision support
- Requires 8K context for memory estimates
- License is Apache‑2.0
Best for
- Chatbots needing long context
- Rapid prototyping on limited GPU
- Integrating WebSearch into LLM workflows
Who it’s for. Developers and researchers who need a compact LLaMA‑style model with extended context. The model is suitable for edge deployments and rapid experimentation without extensive fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 1.1 GB | 2.3 GB | Fits | Get file → | |
| Q2_K | 1.2 GB | 2.4 GB | Fits | Get file → | |
| IQ3_XS | 1.3 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.6 GB | Fits | Get file → | |
| IQ3_M | 1.4 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q2_K_L | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_L | 1.6 GB | 2.8 GB | Fits | Get file → | |
| IQ4_XS | 1.7 GB | 2.8 GB | Fits | Get file → | |
| Q4_0 | 1.7 GB | 2.9 GB | Fits | Get file → | |
| IQ4_NL | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_XL | 1.9 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_L | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_S | 2.1 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_M | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_L | 2.3 GB | 3.5 GB | Fits | Get file → | |
| Q6_K | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q6_K_L | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 3.1 GB | 4.3 GB | Fits | Get file → | |
| F16 | 5.8 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.81 GB, estimated 3 GB memory at 8K context). If 12 GB VRAM is available, Q4_K_L (2.04 GB, 3.2 GB memory) or Q5_K_S (2.05 GB, 3.2 GB memory) offer higher quality. For 16 GB VRAM, Q5_K_L (2.29 GB, 3.5 GB memory) or Q6_K (2.4 GB, 3.6 GB memory) provide a balance between size and precision.
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_L (2.5 GB file, about 3.7 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 IQ2_M at 1.1 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
Source
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: IQ2_M is 1.1 GB, Q2_K is 1.2 GB, IQ3_XS is 1.3 GB, Q3_K_S is 1.4 GB, IQ3_M is 1.4 GB, Q3_K_M is 1.5 GB and 16 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 bartowski/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.
Can I run Megrez 3B Instruct on 8 GB VRAM?
Yes, the Q4_K_M quantization is 1.81 GB and requires approximately 3 GB of VRAM at 8K context, which fits within 8 GB.
Does the model support image inputs?
No, Megrez 3B Instruct does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.