MiniChat 1.5 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 14 quants, from 1.3 GB (Q2_K) to 3.2 GB (Q8_0).
MiniChat 1.5 3B – a distilled LLaMA2‑based chat model
MiniChat 1.5 3B is a 3.02 billion‑parameter language model distilled from LLaMA2‑7B. It supports a 4096‑token context window and is optimized for chat applications. The model is available in multiple GGUF quantizations.
Good at
- Chat‑style dialogue
- Fast inference on modest hardware
- Good balance of size and performance
Limits
- No vision support
- License requires compliance with LLaMA2 terms
- Limited to 4096‑token context
Best for
- Building lightweight chatbots
- Running on 8 GB VRAM setups
- Rapid prototyping of conversational agents
Who it’s for. Developers needing a small yet capable chat model for local deployment. Researchers exploring distilled LLaMA2 variants. Hobbyists wanting to run a chat model on consumer GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_L | 1.6 GB | 3.3 GB | Fits | Get file → | |
| Q4_0 | 1.7 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 3.6 GB | Fits | Get file → | |
| Q4_1 | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q5_0 | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.9 GB | Fits | Get file → | |
| Q5_1 | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 3.2 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M or Q4_K_S (1.85 GB or 1.76 GB) are suitable, estimating 4.8 GB RAM usage at 8 k context. If 12 GB VRAM is available, Q5_K_M (2.15 GB) or Q5_0 (2.10 GB) provide better quality with 5.1 GB or 5.0 GB memory usage. Larger quants like Q8_0 require 3.21 GB and 6.1 GB RAM, suitable for 16 GB VRAM systems.
What GPU do you need for MiniChat 1.5 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).
Which MiniChat 1.5 3B quant should you choose?
Q4_K_M is the usual starting point for MiniChat 1.5 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 1.3 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 MiniChat 1.5 3B
How much VRAM does MiniChat 1.5 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 MiniChat 1.5 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 MiniChat 1.5 3B GGUF?
It depends on the quant: Q2_K is 1.3 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 1.8 GB and 8 more.
What context length does MiniChat 1.5 3B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.4 GB at 8K and 1.2 GB at 4K.
Where can I download MiniChat 1.5 3B GGUF?
The files are on Hugging Face in the tsunemoto/MiniChat-1.5-3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run MiniChat 1.5 3B on 8 GB VRAM?
Yes, use Q4_K_M or Q4_K_S quantizations; they fit within 8 GB VRAM and use about 4.8 GB RAM at 8 k context.
Does the model support image inputs?
No, MiniChat 1.5 3B is a text‑only model and does not support vision.
What license applies to this model?
The model must comply with the LLaMA2 license, as it is derived from LLaMA2.