Irbis-7b-v0.1 needs about 6.1 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 1.7 GB (IQ1_S) to 6.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Irbis‑7B v0.1 – a 7.47B‑parameter LLM optimized for Kazakh
Irbis‑7B v0.1 is a 7.47B‑parameter transformer model tailored for Kazakh. It uses an expanded tokenizer with 60k tokens and was pre‑trained on 20 GB of Kazakh and some Russian text. The model supports a 32 768‑token context window.
Good at
- Large context handling
- Kazakh language support
- Fast generation with optimized tokenizer
Limits
- No vision support
- No explicit language list beyond Kazakh
- Requires 8 k context for memory estimates
Best for
- Local Kazakh text generation
- Chatbots in Kazakh
- Language research
Who it’s for. Developers and researchers needing a lightweight LLM for Kazakh language tasks. The model is released under the MIT license and can be run with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.7 GB | 3.3 GB | Fits | Get file → | |
| IQ1_M | 1.9 GB | 3.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.1 GB | 3.7 GB | Fits | Get file → | |
| IQ2_XS | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ2_S | 2.4 GB | 4.0 GB | Fits | Get file → | |
| IQ2_M | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q2_K | 2.9 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XXS | 3.0 GB | 4.5 GB | Fits | Get file → | |
| IQ3_XS | 3.2 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_S | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_S | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_M | 3.4 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_M | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_L | 4.0 GB | 5.5 GB | Fits | Get file → | |
| IQ4_XS | 4.1 GB | 5.6 GB | Fits | Get file → | |
| Q4_0 | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q5_K_S | 5.2 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_M | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q6_K | 6.1 GB | 7.7 GB | Tight | Get file → |
For 8 GB VRAM, use IQ1_S (1.73 GB, 3.3 GB RAM) or IQ1_M (1.87 GB, 3.4 GB RAM). If 12 GB VRAM is available, IQ2_S (2.44 GB, 4 GB RAM) or Q2_K (2.85 GB, 4.4 GB RAM) provide better quality. Higher quants like Q5_K_M (5.31 GB, 6.9 GB RAM) need 16 GB VRAM or more.
What GPU do you need for Irbis-7b-v0.1?
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 IQ2_S (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_S (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.7 GB in use).
Which Irbis-7b-v0.1 quant should you choose?
Q4_K_M is the usual starting point for Irbis-7b-v0.1: it balances file size and quality well. Here it is a 4.5 GB file.
If memory is tight, the smallest file is IQ1_S at 1.7 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 Irbis-7b-v0.1
How much VRAM does Irbis-7b-v0.1 need?
About 6.1 GB at Q4_K_M with an 8K context window. That is the 4.5 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 Irbis-7b-v0.1 on an 8 GB GPU?
Yes, with Q6_K: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Irbis-7b-v0.1 GGUF?
It depends on the quant: IQ1_S is 1.7 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.4 GB, IQ2_M is 2.6 GB and 15 more.
What context length does Irbis-7b-v0.1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Irbis-7b-v0.1 GGUF?
The files are on Hugging Face in the mradermacher/Irbis-7b-v0.1-i1-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 Irbis-7b-v0.1 use?
Hugging Face lists the license as mit. 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 Irbis‑7B on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quant. They fit within 8 GB VRAM and require about 3.3–3.4 GB RAM.
Does Irbis‑7B support other languages?
The model is primarily trained for Kazakh, with some Russian data. No explicit support for other languages is documented.
What context length does Irbis‑7B support?
It supports up to 32 768 tokens, as specified in the training context tokens.