Hari Q2.5 Thinking needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.0 GB to 64.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Hari Q2.5 Thinking is a 72.7B-parameter Hari model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 24 quant files, from 0.0 GB to 64.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_S | 22.7 GB | 25.9 GB | Too big | Get file → | |
| IQ1_M | 23.7 GB | 26.9 GB | Too big | Get file → | |
| IQ2_XXS | 25.5 GB | 28.7 GB | Too big | Get file → | |
| IQ2_XS | 27.1 GB | 30.2 GB | Too big | Get file → | |
| IQ2_S | 27.9 GB | 31.1 GB | Too big | Get file → | |
| IQ2_M | 29.3 GB | 32.5 GB | Too big | Get file → | |
| Q2_K_S | 29.6 GB | 32.8 GB | Too big | Get file → | |
| Q2_K | 29.8 GB | 33.0 GB | Too big | Get file → | |
| IQ3_XXS | 31.8 GB | 35.0 GB | Too big | Get file → | |
| IQ3_XS | 32.8 GB | 36.0 GB | Too big | Get file → | |
| IQ3_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| Q3_K_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| IQ3_M | 35.5 GB | 38.7 GB | Too big | Get file → | |
| Q3_K_M | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q3_K_L | 39.5 GB | 42.7 GB | Too big | Get file → | |
| IQ4_XS | 39.7 GB | 42.9 GB | Too big | Get file → | |
| Q4_0 | 41.4 GB | 44.6 GB | Too big | Get file → | |
| Q4_K_S | 43.9 GB | 47.1 GB | Too big | Get file → | |
| Q4_1 | 45.7 GB | 48.9 GB | Too big | Get file → | |
| Q4_K_M | 47.4 GB | 50.6 GB | Too big | Get file → | |
| Q5_K_S | 51.4 GB | 54.6 GB | Too big | Get file → | |
| Q5_K_M | 54.4 GB | 57.6 GB | Too big | Get file → | |
| Q6_K | 64.3 GB | 67.5 GB | Too big | Get file → |
What GPU do you need for Hari Q2.5 Thinking?
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: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 32 GB VRAM: the best quant that fits is IQ2_S (27.9 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).
Which Hari Q2.5 Thinking quant should you choose?
Q4_K_M is the usual starting point for Hari Q2.5 Thinking: it balances file size and quality well. Here it is a 47.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hari Q2.5 Thinking
How much VRAM does Hari Q2.5 Thinking need?
About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 Hari Q2.5 Thinking on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hari Q2.5 Thinking GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 22.7 GB, IQ1_M is 23.7 GB, IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_S is 27.9 GB and 18 more.
What context length does Hari Q2.5 Thinking 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 Hari Q2.5 Thinking GGUF?
The files are on Hugging Face in the mradermacher/hari-q2.5-Thinking-i1-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 Hari Q2.5 Thinking 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.