GeM2 Llamion 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 22 quants, from 5.5 GB (Q2_K) to 15.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.
GeM2 Llamion 14B LongChat – 14.5B parameter LLaMA model with 200K token context
GeM2 Llamion 14B LongChat is a 14.5B parameter LLaMA‑based model trained on a 200000 token context. It is released under the apache‑2.0 license and supports long‑form text generation up to 200K tokens.
Good at
- Long‑form text generation
- High token context support
- Large language model capacity
Limits
- No vision support
- Requires large VRAM for higher quants
- No mixture of experts
Best for
- Writing long documents
- Chatting with extended context
- Research summarization
Who it’s for. Developers and researchers needing a large language model with extended context. The model is suitable for applications that require up to 200K token context and can run on systems with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.5 GB | 12.7 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 | 7.1 GB | 14.3 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 | 7.9 GB | 15.1 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 15.5 GB | Too big | Get file → | |
| IQ4_NL | 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 | 8.8 GB | 16.0 GB | Too big | Get file → | |
| Q4_K_M | 8.8 GB | 16.0 GB | Too big | Get file → | |
| Q4_1 | 9.1 GB | 16.4 GB | Too big | Get file → | |
| Q5_0 | 10.0 GB | 17.2 GB | Too big | Get file → | |
| Q5_K_S | 10.0 GB | 17.2 GB | Too big | Get file → | |
| Q5_K | 10.3 GB | 17.5 GB | Too big | Get file → | |
| Q5_K_M | 10.3 GB | 17.5 GB | Too big | Get file → | |
| Q5_1 | 10.9 GB | 18.1 GB | Too big | Get file → | |
| Q6_K | 11.9 GB | 19.1 GB | Too big | Get file → | |
| Q8_0 | 15.4 GB | 22.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (8.27 GB file, 15.5 GB memory at 8 k context). For 12 GB VRAM, Q4_K (8.81 GB file, 16 GB memory) or Q5_0 (10.03 GB file, 17.2 GB memory). For 16 GB VRAM, Q5_K (10.31 GB file, 17.5 GB memory) or Q6_K (11.9 GB file, 19.1 GB memory).
What GPU do you need for GeM2 Llamion 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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_K (8.8 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.4 GB file, about 22.6 GB in use).
Which GeM2 Llamion 14B LongChat quant should you choose?
Q4_K_M is the usual starting point for GeM2 Llamion 14B LongChat: it balances file size and quality well. Here it is a 8.8 GB file.
The Q8_0 file is 15.4 GB, about 1.7 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 5.5 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
Frequently asked questions about GeM2 Llamion 14B LongChat
How much VRAM does GeM2 Llamion 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 GeM2 Llamion 14B LongChat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GeM2 Llamion 14B LongChat GGUF?
It depends on the quant: Q2_K is 5.5 GB, IQ3_XS is 6.1 GB, IQ3_S is 6.4 GB, Q3_K_S is 6.4 GB, IQ3_M is 6.7 GB, Q3_K is 7.1 GB and 16 more.
What context length does GeM2 Llamion 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 GeM2 Llamion 14B LongChat GGUF?
The files are on Hugging Face in the RichardErkhov/vaiv_-_GeM2-Llamion-14B-LongChat-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 GeM2 Llamion 14B LongChat 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 GeM2 Llamion 14B LongChat on 8 GB VRAM?
Use the Q4_0 quant, which requires 15.5 GB memory at 8 k context. This exceeds 8 GB VRAM, so it is not feasible without further optimization.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.