AM-Thinking-v1 needs about 22.5 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 32 quants, from 7.7 GB (TQ1_0) to 65.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
AM-Thinking-v1 is a 32.8B-parameter Thinking model in GGUF format, quantized by Mungert. Its trained context length is 128K tokens. The repository has 32 quant files, from 7.7 GB (TQ1_0) to 65.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 7.7 GB | 10.3 GB | Too big | Get file → | |
| TQ2_0 | 9.1 GB | 11.8 GB | Too big | Get file → | |
| IQ1_S | 10.2 GB | 12.9 GB | Too big | Get file → | |
| IQ1_M | 11.3 GB | 13.9 GB | Too big | Get file → | |
| IQ2_XXS | 11.4 GB | 14.0 GB | Too big | Get file → | |
| Q2_K_S | 12.1 GB | 14.8 GB | Too big | Get file → | |
| Q2_K_M | 12.4 GB | 15.0 GB | Too big | Get file → | |
| IQ2_XS | 12.6 GB | 15.2 GB | Too big | Get file → | |
| IQ2_S | 12.7 GB | 15.3 GB | Too big | Get file → | |
| IQ2_M | 13.2 GB | 15.9 GB | Too big | Get file → | |
| IQ3_XXS | 13.6 GB | 16.3 GB | Too big | Get file → | |
| IQ3_XS | 13.9 GB | 16.5 GB | Too big | Get file → | |
| IQ3_M | 14.7 GB | 17.4 GB | Too big | Get file → | |
| IQ3_S | 14.7 GB | 17.4 GB | Too big | Get file → | |
| Q3_K_S | 15.9 GB | 18.5 GB | Too big | Get file → | |
| Q3_K_M | 16.1 GB | 18.7 GB | Too big | Get file → | |
| IQ4_XS | 17.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_0 | 18.4 GB | 21.1 GB | Too big | Get file → | |
| IQ4_NL | 18.7 GB | 21.3 GB | Too big | Get file → | |
| Q4_K_S | 19.2 GB | 21.8 GB | Too big | Get file → | |
| Q4_K_M | 19.8 GB | 22.5 GB | Too big | Get file → | |
| Q4_1 | 20.5 GB | 23.1 GB | Too big | Get file → | |
| Q5_0 | 22.5 GB | 25.2 GB | Too big | Get file → | |
| Q5_K_S | 23.1 GB | 25.7 GB | Too big | Get file → | |
| Q5_K_M | 23.4 GB | 26.1 GB | Too big | Get file → | |
| Q5_1 | 24.6 GB | 27.2 GB | Too big | Get file → | |
| Q6_K_M | 26.9 GB | 29.5 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 37.5 GB | Too big | Get file → | |
| BF16 | 36.3 GB | 38.9 GB | Too big | Get file → | |
| F16 | 46.9 GB | 49.6 GB | Too big | Get file → | |
| BF16 | 65.5 GB (2 parts) | 68.2 GB | Too big | Get file → | |
| F16 | 65.5 GB (2 parts) | 68.2 GB | Too big | Get file → |
What GPU do you need for AM-Thinking-v1?
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: the best quant that fits is TQ2_0 (9.1 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_M (13.2 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (20.5 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_M (26.9 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (36.3 GB file, about 38.9 GB in use).
Which AM-Thinking-v1 quant should you choose?
Q4_K_M is the usual starting point for AM-Thinking-v1: it balances file size and quality well. Here it is a 19.8 GB file.
The Q8_0 file is 34.8 GB, about 1.8 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 TQ1_0 at 7.7 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AM-Thinking-v1
How much VRAM does AM-Thinking-v1 need?
About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.8 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 AM-Thinking-v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of AM-Thinking-v1 GGUF?
It depends on the quant: TQ1_0 is 7.7 GB, TQ2_0 is 9.1 GB, IQ1_S is 10.2 GB, IQ1_M is 11.3 GB, IQ2_XXS is 11.4 GB, Q2_K_S is 12.1 GB and 26 more.
What context length does AM-Thinking-v1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download AM-Thinking-v1 GGUF?
The files are on Hugging Face in the Mungert/AM-Thinking-v1-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 AM-Thinking-v1 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.