Orion 14B LongChat needs about 16.0 GB of memory at Q4_K_M (a 8.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 3.4 GB (IQ1_S) to 11.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.
Orion 14B LongChat – 14.5B parameter long‑context LLM
Orion 14B LongChat is a 14.5B parameter model fine‑tuned for extremely long texts. It supports a trained context of 200000 tokens and can handle up to 320000 tokens. The model is available in multiple GGUF quantizations.
Good at
- Long‑context conversation
- Coding assistance
- Multilingual text handling
Limits
- No vision support
- License not specified
- Requires large VRAM for higher quants
Best for
- Chatbots needing long memory
- Code generation for large projects
- Document summarization of long PDFs
Who it’s for. Developers and researchers who need a large language model capable of handling very long contexts. The model is suitable for building chat applications, code assistants, and other NLP tools that require extended memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.4 GB | 10.6 GB | Too big | Get file → | |
| IQ1_M | 3.6 GB | 10.8 GB | Too big | Get file → | |
| IQ2_XXS | 4.1 GB | 11.3 GB | Too big | Get file → | |
| IQ2_XS | 4.4 GB | 11.7 GB | Too big | Get file → | |
| IQ2_S | 4.8 GB | 12.0 GB | Too big | Get file → | |
| Q2_K_S | 5.1 GB | 12.3 GB | Too big | Get file → | |
| IQ2_M | 5.1 GB | 12.3 GB | Too big | Get file → | |
| Q2_K | 5.5 GB | 12.7 GB | Too big | Get file → | |
| IQ3_XXS | 5.6 GB | 12.8 GB | Too big | Get file → | |
| IQ3_XS | 6.1 GB | 13.3 GB | Too big | Get file → | |
| IQ3_S | 6.4 GB | 13.6 GB | Too big | Get file → | |
| Q3_K_S | 6.4 GB | 13.6 GB | Too big | Get file → | |
| IQ3_M | 6.7 GB | 13.9 GB | Too big | Get file → | |
| Q3_K_M | 7.1 GB | 14.3 GB | Too big | Get file → | |
| Q3_K_L | 7.8 GB | 15.0 GB | Too big | Get file → | |
| IQ4_XS | 7.8 GB | 15.0 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 15.5 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 15.5 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 15.5 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 15.5 GB | Too big | Get file → | |
| Q4_K_S | 8.3 GB | 15.5 GB | Too big | Get file → | |
| Q4_K_M | 8.8 GB | 16.0 GB | Too big | Get file → | |
| Q5_K_S | 10.0 GB | 17.2 GB | Too big | Get file → | |
| Q5_K_M | 10.3 GB | 17.5 GB | Too big | Get file → | |
| Q6_K | 11.9 GB | 19.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3.36 GB, 10.6 GB memory) or IQ1_M (3.63 GB, 10.8 GB memory). If 12 GB VRAM is available, Q4_K_M (8.81 GB, 16 GB memory) or Q5_K_S (10.03 GB, 17.2 GB memory) provide a good balance of size and performance. Larger quants such as Q6_K (11.9 GB, 19.1 GB memory) require more than 16 GB VRAM.
What GPU do you need for Orion 14B LongChat?
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_S (4.8 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (8.8 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (11.9 GB file, about 19.1 GB in use).
Which Orion 14B LongChat quant should you choose?
Q4_K_M is the usual starting point for Orion 14B LongChat: it balances file size and quality well. Here it is a 8.8 GB file.
If memory is tight, the smallest file is IQ1_S at 3.4 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 Orion 14B LongChat
How much VRAM does Orion 14B LongChat need?
About 16.0 GB at Q4_K_M with an 8K context window. That is the 8.8 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 Orion 14B LongChat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Orion 14B LongChat GGUF?
It depends on the quant: IQ1_S is 3.4 GB, IQ1_M is 3.6 GB, IQ2_XXS is 4.1 GB, IQ2_XS is 4.4 GB, IQ2_S is 4.8 GB, Q2_K_S is 5.1 GB and 19 more.
What context length does Orion 14B LongChat support?
The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.
Where can I download Orion 14B LongChat GGUF?
The files are on Hugging Face in the mradermacher/Orion-14B-LongChat-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Orion 14B LongChat on 8 GB VRAM?
Yes, with IQ1_S or IQ1_M quantizations the model fits within 8 GB VRAM and uses about 10.6–10.8 GB of memory at 8k context.
Does the model support vision tasks?
No, Orion 14B LongChat is a text‑only model with no vision capabilities.
What is the maximum context length I can use?
The model was trained on 200000 tokens and can support up to 320000 tokens in inference.