TeeZee DarkForest 20B v1.1 needs about 1.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.3 GB (Q5_K_S) to 15.0 GB (Q5_1).
TeeZee DarkForest 20B v1.1 is a 20B-parameter Teezee model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 22 quant files, from 0.3 GB (Q5_K_S) to 15.0 GB (Q5_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q5_0 | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q4_1 | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.2 GB | Fits | Get file → | |
| Q4_K | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 2.1 GB | Fits | Get file → | |
| IQ4_NL | 2.0 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_M | 3.0 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 6.7 GB | 7.6 GB | Tight | Get file → | |
| Q2_K | 7.4 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 9.0 GB | Too big | Get file → | |
| IQ3_XS | 8.2 GB | 9.2 GB | Too big | Get file → | |
| Q4_0 | 8.5 GB | 9.5 GB | Too big | Get file → | |
| IQ3_S | 8.7 GB | 9.7 GB | Too big | Get file → | |
| IQ3_M | 9.2 GB | 10.2 GB | Too big | Get file → | |
| Q3_K | 9.7 GB | 10.8 GB | Too big | Get file → | |
| Q3_K_M | 9.7 GB | 10.8 GB | Too big | Get file → | |
| Q6_K | 9.9 GB | 10.9 GB | Too big | Get file → | |
| Q3_K_L | 10.6 GB | 11.8 GB | Too big | Get file → | |
| IQ4_XS | 10.7 GB | 11.9 GB | Too big | Get file → | |
| Q5_K | 14.2 GB | 15.5 GB | Too big | Get file → | |
| Q5_1 | 15.0 GB | 16.4 GB | Too big | Get file → |
What GPU do you need for TeeZee DarkForest 20B v1.1?
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 Q5_K_M (3.0 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (3.0 GB file, about 3.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_S (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (10.7 GB file, about 12.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_1 (15.0 GB file, about 17.3 GB in use).
Which TeeZee DarkForest 20B v1.1 quant should you choose?
Q4_K_M is the usual starting point for TeeZee DarkForest 20B v1.1: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 8.0 GB, about 11.9 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 Q5_K_S at 0.3 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
Frequently asked questions about TeeZee DarkForest 20B v1.1
How much VRAM does TeeZee DarkForest 20B v1.1 need?
About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 TeeZee DarkForest 20B v1.1 on an 8 GB GPU?
Yes, with Q3_K_S: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of TeeZee DarkForest 20B v1.1 GGUF?
It depends on the quant: Q5_K_S is 0.3 GB, Q5_0 is 0.6 GB, Q4_1 is 0.6 GB, Q4_K_M is 0.7 GB, Q4_K is 1.2 GB, Q4_K_S is 1.5 GB and 16 more.
What context length does TeeZee DarkForest 20B v1.1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K).
Where can I download TeeZee DarkForest 20B v1.1 GGUF?
The files are on Hugging Face in the RichardErkhov/TeeZee_-_DarkForest-20B-v1.1-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.