Tigerbot 13b Chat v6 needs about 15.3 GB of memory at Q4_K_M (a 8.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 3.1 GB (IQ1_S) to 11.0 GB (Q6_K).
Tigerbot 13b Chat v6 – 13.4B llama‑based chat model
Tigerbot 13b Chat v6 is a 13.4B parameter llama model trained on 8192 token context. It is released under apache‑2.0 and supports multiple quantizations for efficient inference.
Good at
- Chat‑style dialogue
- Large context handling
- Low‑latency inference with small quants
Limits
- No vision support
- Requires 8k context for full performance
- License is apache‑2.0
Best for
- Chatbot development
- Fine‑tuning on custom data
- Low‑cost inference on edge devices
Who it’s for. Developers and researchers who need a large llama‑based chat model with flexible quantization options. The model is suitable for building chat applications or for further training on specialized corpora.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.1 GB | 10.3 GB | Too big | Get file → | |
| IQ1_M | 3.3 GB | 10.5 GB | Too big | Get file → | |
| IQ2_XXS | 3.7 GB | 10.9 GB | Too big | Get file → | |
| IQ2_XS | 4.1 GB | 11.3 GB | Too big | Get file → | |
| IQ2_S | 4.4 GB | 11.6 GB | Too big | Get file → | |
| Q2_K_S | 4.6 GB | 11.8 GB | Too big | Get file → | |
| IQ2_M | 4.7 GB | 11.9 GB | Too big | Get file → | |
| Q2_K | 5.0 GB | 12.3 GB | Too big | Get file → | |
| IQ3_XXS | 5.2 GB | 12.4 GB | Too big | Get file → | |
| IQ3_XS | 5.6 GB | 12.8 GB | Too big | Get file → | |
| IQ3_S | 5.9 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_S | 5.9 GB | 13.1 GB | Too big | Get file → | |
| IQ3_M | 6.2 GB | 13.4 GB | Too big | Get file → | |
| Q3_K_M | 6.6 GB | 13.8 GB | Too big | Get file → | |
| Q3_K_L | 7.1 GB | 14.4 GB | Too big | Get file → | |
| IQ4_XS | 7.2 GB | 14.4 GB | Too big | Get file → | |
| Q4_0 | 7.6 GB | 14.8 GB | Too big | Get file → | |
| Q4_0 | 7.6 GB | 14.8 GB | Too big | Get file → | |
| Q4_0 | 7.6 GB | 14.8 GB | Too big | Get file → | |
| Q4_0 | 7.6 GB | 14.8 GB | Too big | Get file → | |
| Q4_K_S | 7.7 GB | 14.9 GB | Too big | Get file → | |
| Q4_K_M | 8.1 GB | 15.3 GB | Too big | Get file → | |
| Q5_K_S | 9.2 GB | 16.4 GB | Too big | Get file → | |
| Q5_K_M | 9.5 GB | 16.7 GB | Too big | Get file → | |
| Q6_K | 11.0 GB | 18.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3.07 GB, 10.3 GB memory at 8k context) or IQ1_M (3.31 GB, 10.5 GB). For 12 GB VRAM, Q4_K_M (8.1 GB, 15.3 GB) or Q5_K_M (9.49 GB, 16.7 GB) are suitable. Larger VRAM allows Q6_K (10.96 GB, 18.2 GB).
What GPU do you need for Tigerbot 13b Chat v6?
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_M (4.7 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (8.1 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (11.0 GB file, about 18.2 GB in use).
Which Tigerbot 13b Chat v6 quant should you choose?
Q4_K_M is the usual starting point for Tigerbot 13b Chat v6: it balances file size and quality well. Here it is a 8.1 GB file.
If memory is tight, the smallest file is IQ1_S at 3.1 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 Tigerbot 13b Chat v6
How much VRAM does Tigerbot 13b Chat v6 need?
About 15.3 GB at Q4_K_M with an 8K context window. That is the 8.1 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 Tigerbot 13b Chat v6 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Tigerbot 13b Chat v6 GGUF?
It depends on the quant: IQ1_S is 3.1 GB, IQ1_M is 3.3 GB, IQ2_XXS is 3.7 GB, IQ2_XS is 4.1 GB, IQ2_S is 4.4 GB, Q2_K_S is 4.6 GB and 19 more.
What context length does Tigerbot 13b Chat v6 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.
Where can I download Tigerbot 13b Chat v6 GGUF?
The files are on Hugging Face in the mradermacher/tigerbot-13b-chat-v6-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 Tigerbot 13b Chat v6 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 Tigerbot 13b Chat v6 on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations, which fit 8 GB VRAM and require about 10.3–10.5 GB memory at 8k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.