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 15 quants, from 1.2 GB (Q2_K) to 6.0 GB (F16).
MiniChat-1.5-3B – a 3.02 B parameter LLaMA‑based chat model
MiniChat-1.5-3B is a 3.02 B parameter LLaMA architecture model distilled from LLaMA2‑7B. It was trained with a 4096 token context window and released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Chat‑style interactions
- Fast inference on modest hardware
- Supports 4096 token context
Limits
- No vision support
- Requires 8 k context for memory estimates
- License requires LLaMA2 compliance
Best for
- Local chatbot deployments
- Rapid prototyping of LLM features
- Low‑budget inference
Who it’s for. Developers and researchers who need a lightweight LLaMA‑based chat model that can run on consumer GPUs. The model is suitable for projects requiring a 3 B parameter size with a 4096 token context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.2 GB | 2.9 GB | Fits | Get file → | |
| IQ3_XS | 1.3 GB | 3.0 GB | Fits | Get file → | |
| IQ3_S | 1.4 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 3.1 GB | Fits | Get file → | |
| IQ3_M | 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 → | |
| IQ4_XS | 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 → | |
| Q5_K_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.9 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 → | |
| F16 | 6.0 GB | 7.8 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (1.85 GB file, ~4.8 GB memory). For 16 GB VRAM, Q5_K_M (2.15 GB file, ~5.1 GB memory) or Q6_K (2.48 GB file, ~5.4 GB memory). Higher precision quants like Q8_0 or F16 provide better quality but need more memory.
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).
- 12 GB VRAM: the best quant that fits is F16 (6.0 GB file, about 9.0 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 1.2 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
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 1.2 GB, IQ3_XS is 1.3 GB, IQ3_S is 1.4 GB, Q3_K_S is 1.4 GB, IQ3_M is 1.4 GB, Q3_K_M is 1.5 GB and 9 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 mradermacher/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.
What license does MiniChat-1.5-3B 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 MiniChat-1.5-3B on 8 GB VRAM?
Yes, a Q4_K_M quantization uses about 4.8 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does MiniChat-1.5-3B support image input?
No, the model has no vision capabilities.
What license applies to MiniChat-1.5-3B?
It is released under the Apache‑2.0 license, with compliance to LLaMA2 licensing requirements.