firefly llama2 13B chat needs about 15.2 GB of memory at Q4_K_M (a 8.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.6 GB (Q2_K) to 14.1 GB (Q8_0).
Firefly Llama2 13B Chat – bilingual LLaMA2 model in GGUF format
Firefly Llama2 13B Chat is a 13.3 billion‑parameter Llama model fine‑tuned for Chinese and English dialogue. It is available in multiple GGUF quantisations from Q2_K to Q8_0. The model supports a 4096‑token context window and is licensed under llama2.
Good at
- Chinese dialogue
- English conversation
- Instruction following
Limits
- No vision support
- Requires GPU for best performance
- License restricts commercial use
Best for
- Local chatbot deployment
- Multilingual Q&A
- Fine‑tuning on custom data
Who it’s for. Developers and researchers needing a bilingual LLaMA2 model for local inference. The model is suitable for those who can run GGUF files on llama.cpp or compatible frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.6 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_S | 5.8 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_M | 6.5 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_L | 7.1 GB | 10.9 GB | Too big | Get file → | |
| Q4_0 | 7.5 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_S | 7.6 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_M | 8.0 GB | 11.9 GB | Too big | Get file → | |
| Q5_0 | 9.2 GB | 13.0 GB | Too big | Get file → | |
| Q5_K_S | 9.2 GB | 13.0 GB | Too big | Get file → | |
| Q5_K_M | 9.4 GB | 13.3 GB | Too big | Get file → | |
| Q6_K | 10.9 GB | 14.7 GB | Too big | Get file → | |
| Q8_0 | 14.1 GB | 17.9 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (8.03 GB) or Q5_K_S (9.15 GB) are suitable. If you have 12 GB VRAM, Q5_K_M (9.41 GB) or Q6_K (10.88 GB) provide better quality. Larger VRAM allows Q8_0 (14.09 GB) for maximum fidelity.
What GPU do you need for firefly llama2 13B chat?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_K_M (8.0 GB file, about 15.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 21.3 GB in use).
Which firefly llama2 13B chat quant should you choose?
Q4_K_M is the usual starting point for firefly llama2 13B chat: it balances file size and quality well. Here it is a 8.0 GB file.
The Q8_0 file is 14.1 GB, about 1.8 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 5.6 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 firefly llama2 13B chat
How much VRAM does firefly llama2 13B chat need?
About 15.2 GB at Q4_K_M with an 8K context window. That is the 8.0 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 firefly llama2 13B chat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of firefly llama2 13B chat GGUF?
It depends on the quant: Q2_K is 5.6 GB, Q3_K_S is 5.8 GB, Q3_K_M is 6.5 GB, Q3_K_L is 7.1 GB, Q4_0 is 7.5 GB, Q4_K_S is 7.6 GB and 6 more.
What context length does firefly llama2 13B chat 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 firefly llama2 13B chat GGUF?
The files are on Hugging Face in the TheBloke/firefly-llama2-13B-chat-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 firefly llama2 13B chat use?
Hugging Face lists the license as llama2. 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 Firefly Llama2 13B Chat on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_S quantisations which fit within 8 GB VRAM and provide reasonable performance.
Does this model support image input?
No, the model has no vision capabilities and only processes text.
What is the maximum context length?
The model supports a context length of 4096 tokens.