Vikhr-Llama-3.2-1B-instruct needs about 1.6 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 31 quants, from 0.4 GB (IQ1_S) to 2.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.
Vikhr-Llama-3.2-1B-instruct – compact Russian‑focused Llama model
Vikhr-Llama-3.2-1B-instruct is a 1.24 billion‑parameter Llama model fine‑tuned on the GrandMaster‑PRO‑MAX dataset. It supports 131072‑token context and is optimized for low‑power or mobile deployment. The model is available in multiple GGUF quantisations.
Good at
- Russian language instruction handling
- Chain‑of‑Thought support
- Low‑memory inference
Limits
- No vision capability
- Requires at least 1.2 GB VRAM for 8 k context
- License: llama3.2
Best for
- Chatbots on mobile devices
- Local Russian language assistants
- Low‑resource inference
Who it’s for. Developers building Russian‑language applications on limited hardware. Researchers needing a small, efficient Llama variant for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.4 GB | 1.2 GB | Fits | Get file → | |
| IQ1_M | 0.4 GB | 1.2 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.2 GB | Fits | Get file → | |
| IQ2_XS | 0.5 GB | 1.2 GB | Fits | Get file → | |
| IQ2_S | 0.5 GB | 1.3 GB | Fits | Get file → | |
| IQ2_M | 0.5 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XXS | 0.6 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.6 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XS | 0.6 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.6 GB | 1.4 GB | Fits | Get file → | |
| IQ3_S | 0.6 GB | 1.4 GB | Fits | Get file → | |
| IQ3_M | 0.7 GB | 1.4 GB | Fits | Get file → | |
| Q3_K | 0.7 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.7 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.7 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.7 GB | 1.5 GB | Fits | Get file → | |
| Q4_0 | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q4_0 | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ4_NL | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_S | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q4_K | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q4_1 | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q5_0 | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q5_K | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q5_1 | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.3 GB | 2.1 GB | Fits | Get file → | |
| F16 | 2.5 GB | 3.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K or Q4_K_M (≈1.5 GB file, 1.6 GB memory). For 4 GB VRAM, choose Q3_K or Q3_K_S (≈0.69 GB file, 1.5 GB memory). For 2 GB VRAM, use Q2_K (≈0.58 GB file, 1.3 GB memory).
What GPU do you need for Vikhr-Llama-3.2-1B-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 F16 (2.5 GB file, about 3.2 GB in use).
Which Vikhr-Llama-3.2-1B-instruct quant should you choose?
Q4_K_M is the usual starting point for Vikhr-Llama-3.2-1B-instruct: it balances file size and quality well. Here it is a 0.8 GB file.
The Q8_0 file is 1.3 GB, about 1.6 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 IQ1_S at 0.4 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 Vikhr-Llama-3.2-1B-instruct
How much VRAM does Vikhr-Llama-3.2-1B-instruct need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.8 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 Vikhr-Llama-3.2-1B-instruct on an 8 GB GPU?
Yes, with F16: the 2.5 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Vikhr-Llama-3.2-1B-instruct GGUF?
It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.5 GB, IQ2_S is 0.5 GB, IQ2_M is 0.5 GB and 25 more.
What context length does Vikhr-Llama-3.2-1B-instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.
Where can I download Vikhr-Llama-3.2-1B-instruct GGUF?
The files are on Hugging Face in the Vikhrmodels/Vikhr-Llama-3.2-1B-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 Vikhr-Llama-3.2-1B-instruct use?
Hugging Face lists the license as llama3.2. 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 Vikhr-Llama-3.2-1B-instruct on 8 GB VRAM?
Yes, quantisations such as Q4_K or Q4_K_M fit within 8 GB VRAM and use about 1.6 GB memory at 8 k context.
Does this model support vision tasks?
No, Vikhr-Llama-3.2-1B-instruct does not include vision capability.
What is the recommended temperature for generation?
The recommended temperature is 0.3 for optimal responses.