Larson 72b Dpo 1.0.4 needs about 65.7 GB of memory at Q4_K_M (a 43.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 21 quants, from 16.2 GB (IQ1_S) to 49.9 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.
Larson 72b Dpo 1.0.4 is a 72.3B-parameter Larson model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 21 quant files, from 16.2 GB (IQ1_S) to 49.9 GB (Q5_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 16.2 GB | 38.2 GB | Too big | Get file → | |
| IQ1_M | 17.6 GB | 39.5 GB | Too big | Get file → | |
| IQ2_XXS | 19.8 GB | 41.8 GB | Too big | Get file → | |
| IQ2_XS | 21.7 GB | 43.7 GB | Too big | Get file → | |
| IQ2_S | 23.4 GB | 45.4 GB | Too big | Get file → | |
| Q2_K_S | 24.8 GB | 46.8 GB | Too big | Get file → | |
| IQ2_M | 25.2 GB | 47.1 GB | Too big | Get file → | |
| Q2_K | 27.1 GB | 49.1 GB | Too big | Get file → | |
| IQ3_XXS | 27.7 GB | 49.7 GB | Too big | Get file → | |
| IQ3_XS | 29.9 GB | 51.9 GB | Too big | Get file → | |
| IQ3_S | 31.6 GB | 53.5 GB | Too big | Get file → | |
| Q3_K_S | 31.6 GB | 53.5 GB | Too big | Get file → | |
| IQ3_M | 33.3 GB | 55.2 GB | Too big | Get file → | |
| Q3_K_M | 35.3 GB | 57.3 GB | Too big | Get file → | |
| Q3_K_L | 38.5 GB | 60.5 GB | Too big | Get file → | |
| IQ4_XS | 38.8 GB | 60.8 GB | Too big | Get file → | |
| IQ4_NL | 41.0 GB | 63.0 GB | Too big | Get file → | |
| Q4_0 | 41.1 GB | 63.1 GB | Too big | Get file → | |
| Q4_K_S | 41.3 GB | 63.3 GB | Too big | Get file → | |
| Q4_K_M | 43.8 GB | 65.7 GB | Too big | Get file → | |
| Q5_K_S | 49.9 GB | 71.9 GB | Too big | Get file → |
What GPU do you need for Larson 72b Dpo 1.0.4?
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: the best quant that fits is IQ2_M (25.2 GB file, about 47.1 GB in use).
Which Larson 72b Dpo 1.0.4 quant should you choose?
Q4_K_M is the usual starting point for Larson 72b Dpo 1.0.4: it balances file size and quality well. Here it is a 43.8 GB file.
If memory is tight, the smallest file is IQ1_S at 16.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Larson 72b Dpo 1.0.4
How much VRAM does Larson 72b Dpo 1.0.4 need?
About 65.7 GB at Q4_K_M with an 8K context window. That is the 43.8 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 Larson 72b Dpo 1.0.4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 38.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Larson 72b Dpo 1.0.4 GGUF?
It depends on the quant: IQ1_S is 16.2 GB, IQ1_M is 17.6 GB, IQ2_XXS is 19.8 GB, IQ2_XS is 21.7 GB, IQ2_S is 23.4 GB, Q2_K_S is 24.8 GB and 15 more.
What context length does Larson 72b Dpo 1.0.4 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.
Where can I download Larson 72b Dpo 1.0.4 GGUF?
The files are on Hugging Face in the mradermacher/larson-72b-dpo-1.0.4-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 Larson 72b Dpo 1.0.4 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.