Blossom v2 Baichuan 13b needs about 15.8 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 4.0 GB (IQ1_S) to 11.6 GB (Q6_K).
Blossom v2 Baichuan 13b – a 13.3B parameter conversational model
Blossom v2 Baichuan 13b is a 13.3B parameter model based on Baichuan. It was instruction tuned on a mix of Wizard, Dolphin, Blossom chat, and Blossom math datasets. The model supports a 4096 token context window and is released under the apache-2.0 license.
Good at
- Conversational dialogue
- Instruction following
- Multi‑turn chat
Limits
- No vision support
- Requires 8k context for memory estimates
- No mixture of experts
Best for
- Chatbot development
- Prompt engineering experiments
- Small‑to‑medium inference workloads
Who it’s for. Developers and researchers who need a conversational LLM with a 13.3B parameter size and a 4096 token context window. The model is suitable for local deployment on systems with sufficient VRAM and RAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.0 GB | 7.9 GB | Tight | Get file → | |
| IQ1_M | 4.2 GB | 8.1 GB | Too big | Get file → | |
| IQ2_XXS | 4.5 GB | 8.4 GB | Too big | Get file → | |
| IQ2_XS | 4.8 GB | 8.6 GB | Too big | Get file → | |
| IQ2_S | 5.1 GB | 8.9 GB | Too big | Get file → | |
| Q2_K_S | 5.2 GB | 9.1 GB | Too big | Get file → | |
| IQ2_M | 5.3 GB | 9.2 GB | Too big | Get file → | |
| Q2_K | 5.4 GB | 9.2 GB | Too big | Get file → | |
| IQ3_XXS | 5.6 GB | 9.5 GB | Too big | Get file → | |
| IQ3_XS | 5.9 GB | 9.8 GB | Too big | Get file → | |
| IQ3_S | 6.2 GB | 10.1 GB | Too big | Get file → | |
| Q3_K_S | 6.2 GB | 10.1 GB | Too big | Get file → | |
| IQ3_M | 6.5 GB | 10.4 GB | Too big | Get file → | |
| Q3_K_M | 6.8 GB | 10.7 GB | Too big | Get file → | |
| IQ4_XS | 7.2 GB | 11.1 GB | Too big | Get file → | |
| Q3_K_L | 7.3 GB | 11.1 GB | Too big | Get file → | |
| Q4_0 | 7.5 GB | 11.4 GB | Too big | Get file → | |
| Q4_0 | 7.5 GB | 11.4 GB | Too big | Get file → | |
| Q4_0 | 7.5 GB | 11.4 GB | Too big | Get file → | |
| Q4_0 | 7.6 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_S | 7.9 GB | 11.8 GB | Too big | Get file → | |
| Q4_K_M | 8.6 GB | 12.4 GB | Too big | Get file → | |
| Q5_K_S | 9.3 GB | 13.2 GB | Too big | Get file → | |
| Q5_K_M | 9.8 GB | 13.7 GB | Too big | Get file → | |
| Q6_K | 11.6 GB | 15.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.03 GB) or IQ1_M (4.21 GB). If you have 12 GB VRAM, IQ2_S (5.08 GB) or Q2_K_S (5.22 GB) are good choices. For 16 GB VRAM, Q5_K_S (9.34 GB) or Q5_K_M (9.85 GB) provide higher quality. Memory estimates are approximate.
What GPU do you need for Blossom v2 Baichuan 13b?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ2_XS (4.8 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (8.6 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (11.6 GB file, about 18.8 GB in use).
Which Blossom v2 Baichuan 13b quant should you choose?
Q4_K_M is the usual starting point for Blossom v2 Baichuan 13b: it balances file size and quality well. Here it is a 8.6 GB file.
If memory is tight, the smallest file is IQ1_S at 4.0 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 Blossom v2 Baichuan 13b
How much VRAM does Blossom v2 Baichuan 13b need?
About 15.8 GB at Q4_K_M with an 8K context window. That is the 8.6 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 Blossom v2 Baichuan 13b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Blossom v2 Baichuan 13b GGUF?
It depends on the quant: IQ1_S is 4.0 GB, IQ1_M is 4.2 GB, IQ2_XXS is 4.5 GB, IQ2_XS is 4.8 GB, IQ2_S is 5.1 GB, Q2_K_S is 5.2 GB and 19 more.
What context length does Blossom v2 Baichuan 13b support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download Blossom v2 Baichuan 13b GGUF?
The files are on Hugging Face in the mradermacher/blossom-v2-baichuan-13b-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 Blossom v2 Baichuan 13b 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 Blossom v2 Baichuan 13b on 8 GB VRAM?
Yes, use the IQ1_S or IQ1_M quantized files, which are 4.03 GB and 4.21 GB respectively.
Does the model support vision tasks?
No, the model does not have vision capabilities.
What is the maximum context length?
The model supports a 4096 token context window.