Trickser Theta 4 70B calibrated needs about 61.1 GB of memory at Q6_K (a 57.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 49.9 GB (Q5_K_M) to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Trickser Theta 4 70B calibrated is a 70.6B-parameter Trickster model in GGUF format, quantized by Babsie. Its trained context length is 128K tokens. The repository has 3 quant files, from 49.9 GB (Q5_K_M) to 75.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 49.9 GB | 53.1 GB | Too big | Get file → | |
| Q6_K | 57.9 GB | 61.1 GB | Too big | Get file → | |
| Q8_0 | 75.0 GB | 78.2 GB | Too big | Get file → |
What GPU do you need for Trickser Theta 4 70B calibrated?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Trickser Theta 4 70B calibrated quant should you choose?
Q6_K (57.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q5_K_M at 49.9 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Trickser Theta 4 70B calibrated
How much VRAM does Trickser Theta 4 70B calibrated need?
About 61.1 GB at Q6_K with an 8K context window. That is the 57.9 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 Trickser Theta 4 70B calibrated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 53.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Trickser Theta 4 70B calibrated GGUF?
It depends on the quant: Q5_K_M is 49.9 GB, Q6_K is 57.9 GB, Q8_0 is 75.0 GB.
What context length does Trickser Theta 4 70B calibrated support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Trickser Theta 4 70B calibrated GGUF?
The files are on Hugging Face in the Babsie/Trickser_Theta_4_70B_calibrated_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 Trickser Theta 4 70B calibrated use?
Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.