chargoddard llama 2 26b trenchcoat stack needs about 6.7 GB of memory at Q4_K_M (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 2.6 GB (IQ4_XS) to 27.3 GB (Q8_0).
Chargoddard Llama 2 26B Trenchcoat Stack – 25.7 B parameter model
Chargoddard Llama 2 26B Trenchcoat Stack is a 25.7 B parameter Llama model quantized by RichardErkhov. It is available in multiple GGUF quantizations ranging from IQ4_XS to Q8_0. The model has no fine‑tuning and retains coherence across generations.
Good at
- Large context generation
- Coherent multi‑turn dialogue
- High‑capacity language modeling
Limits
- No vision support
- License not specified
- Large memory requirement for high‑quality quants
Best for
- Chatbots needing high token limits
- Research prototyping on local hardware
- Generating long technical documents
Who it’s for. Developers and researchers who need a large Llama model on local hardware. The model is suitable for those who can manage the memory demands of the higher‑quality quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 5.5 GB | 6.7 GB | Fits | Get file → | |
| Q2_K | 9.5 GB | 11.2 GB | Too big | Get file → | |
| Q4_K_S | 10.3 GB | 12.0 GB | Too big | Get file → | |
| IQ3_XS | 10.5 GB | 12.3 GB | Too big | Get file → | |
| IQ3_S | 11.1 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_S | 11.1 GB | 12.9 GB | Too big | Get file → | |
| IQ3_M | 11.8 GB | 13.7 GB | Too big | Get file → | |
| Q3_K | 12.5 GB | 14.5 GB | Too big | Get file → | |
| Q3_K_M | 12.5 GB | 14.5 GB | Too big | Get file → | |
| Q3_K_L | 13.7 GB | 15.8 GB | Too big | Get file → | |
| Q4_0 | 14.5 GB | 16.7 GB | Too big | Get file → | |
| IQ4_NL | 14.6 GB | 16.8 GB | Too big | Get file → | |
| Q4_K | 15.5 GB | 17.9 GB | Too big | Get file → | |
| Q4_1 | 16.1 GB | 18.5 GB | Too big | Get file → | |
| Q5_0 | 17.7 GB | 20.3 GB | Too big | Get file → | |
| Q5_K_S | 17.7 GB | 20.3 GB | Too big | Get file → | |
| Q5_K | 18.2 GB | 20.9 GB | Too big | Get file → | |
| Q5_K_M | 18.2 GB | 20.9 GB | Too big | Get file → | |
| Q5_1 | 19.3 GB | 22.1 GB | Too big | Get file → | |
| Q6_K | 21.1 GB | 24.1 GB | Too big | Get file → | |
| Q8_0 | 27.3 GB | 31.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (2.57 GB file, 3.4 GB memory) or Q4_K_M (5.5 GB file, 6.7 GB memory). For 16 GB VRAM, Q4_K (15.5 GB file, 17.9 GB memory) or Q5_K (18.21 GB file, 20.9 GB memory) are suitable. Higher quants require more than 24 GB VRAM.
What GPU do you need for chargoddard llama 2 26b trenchcoat stack?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is IQ4_XS (2.6 GB file, about 3.4 GB in use).
- 6 GB VRAM: the best quant that fits is IQ4_XS (2.6 GB file, about 3.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.5 GB file, about 6.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_S (10.3 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (13.7 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_1 (19.3 GB file, about 22.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (27.3 GB file, about 31.1 GB in use).
Which chargoddard llama 2 26b trenchcoat stack quant should you choose?
Q4_K_M is the usual starting point for chargoddard llama 2 26b trenchcoat stack: it balances file size and quality well. Here it is a 5.5 GB file.
The Q8_0 file is 27.3 GB, about 5.0 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 IQ4_XS at 2.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about chargoddard llama 2 26b trenchcoat stack
How much VRAM does chargoddard llama 2 26b trenchcoat stack need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.5 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 chargoddard llama 2 26b trenchcoat stack on an 8 GB GPU?
Yes, with Q4_K_M: the 5.5 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of chargoddard llama 2 26b trenchcoat stack GGUF?
It depends on the quant: IQ4_XS is 2.6 GB, Q4_K_M is 5.5 GB, Q2_K is 9.5 GB, Q4_K_S is 10.3 GB, IQ3_XS is 10.5 GB, IQ3_S is 11.1 GB and 16 more.
Where can I download chargoddard llama 2 26b trenchcoat stack GGUF?
The files are on Hugging Face in the RichardErkhov/chargoddard_-_llama-2-26b-trenchcoat-stack-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 this model on 8 GB VRAM?
Yes, with the IQ4_XS quantization (2.57 GB file, 3.4 GB estimated memory).
Does this model support vision?
No, the model has no vision capability.
Is the model fine‑tuned?
No, the model was not fine‑tuned and retains coherence from the base Llama 2 architecture.