Miqu 70B Alpaca DPO i1 needs about 44.9 GB of memory at Q4_K_M (a 41.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 14.9 GB (IQ1_S) to 49.1 GB (Q5_K_M).
70B‑parameter Miqu Alpaca DPO model in GGUF format
Miqu 70B Alpaca DPO i1 is a 70 billion‑parameter llama architecture model. It is a DPO‑trained variant of Miqu, tuned on Alpaca format to reduce censorship while retaining safety warnings. The model is available in multiple GGUF quantizations.
Good at
- Alpaca prompt style
- Reduced censorship compared to base Miqu
- Large context support up to 32 k tokens
Limits
- No vision support
- License not specified
- Requires large VRAM for higher quants
Best for
- Fine‑tuning with Alpaca prompts
- Research on DPO‑trained models
- Running on high‑end GPUs
Who it’s for. Users who need a large llama model with Alpaca prompt compatibility and reduced censorship. Suitable for developers and researchers working on language model fine‑tuning or evaluation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 14.9 GB | 18.1 GB | Too big | Get file → | |
| IQ1_M | 15.9 GB | 19.1 GB | Too big | Get file → | |
| IQ2_XXS | 18.6 GB | 21.8 GB | Too big | Get file → | |
| IQ2_XS | 20.7 GB | 23.9 GB | Too big | Get file → | |
| IQ2_S | 21.7 GB | 24.9 GB | Too big | Get file → | |
| IQ2_M | 23.6 GB | 26.8 GB | Too big | Get file → | |
| Q2_K | 25.8 GB | 29.0 GB | Too big | Get file → | |
| IQ3_XXS | 26.9 GB | 30.1 GB | Too big | Get file → | |
| IQ3_XS | 28.6 GB | 31.8 GB | Too big | Get file → | |
| IQ3_S | 30.2 GB | 33.4 GB | Too big | Get file → | |
| Q3_K_S | 30.2 GB | 33.4 GB | Too big | Get file → | |
| IQ3_M | 31.3 GB | 34.4 GB | Too big | Get file → | |
| Q3_K_M | 33.6 GB | 36.8 GB | Too big | Get file → | |
| Q3_K_L | 36.5 GB | 39.6 GB | Too big | Get file → | |
| IQ4_XS | 37.1 GB | 40.3 GB | Too big | Get file → | |
| IQ4_NL | 39.3 GB | 42.4 GB | Too big | Get file → | |
| Q4_0 | 39.3 GB | 42.5 GB | Too big | Get file → | |
| Q4_K_S | 39.6 GB | 42.7 GB | Too big | Get file → | |
| Q4_K_M | 41.7 GB | 44.9 GB | Too big | Get file → | |
| Q5_K_S | 47.8 GB | 51.0 GB | Too big | Get file → | |
| Q5_K_M | 49.1 GB | 52.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (14.88 GB file, ~18 GB VRAM). For 16 GB VRAM, IQ2_S (21.7 GB file, ~25 GB VRAM). For 24 GB VRAM, Q4_K_M (41.73 GB file, ~45 GB VRAM). Memory estimates are approximate.
What GPU do you need for Miqu 70B Alpaca DPO i1?
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: the best quant that fits is IQ2_XS (20.7 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XS (28.6 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (41.7 GB file, about 44.9 GB in use).
Which Miqu 70B Alpaca DPO i1 quant should you choose?
Q4_K_M is the usual starting point for Miqu 70B Alpaca DPO i1: it balances file size and quality well. Here it is a 41.7 GB file.
If memory is tight, the smallest file is IQ1_S at 14.9 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 Miqu 70B Alpaca DPO i1
How much VRAM does Miqu 70B Alpaca DPO i1 need?
About 44.9 GB at Q4_K_M with an 8K context window. That is the 41.7 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 Miqu 70B Alpaca DPO i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Miqu 70B Alpaca DPO i1 GGUF?
It depends on the quant: IQ1_S is 14.9 GB, IQ1_M is 15.9 GB, IQ2_XXS is 18.6 GB, IQ2_XS is 20.7 GB, IQ2_S is 21.7 GB, IQ2_M is 23.6 GB and 15 more.
What context length does Miqu 70B Alpaca DPO i1 support?
The GGUF header lists a trained context length of 32,764 tokens (32K). 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 Miqu 70B Alpaca DPO i1 GGUF?
The files are on Hugging Face in the mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Use the IQ1_S quant; it requires about 18 GB VRAM at 8k context, so 8 GB VRAM is insufficient.
Does this model support vision?
No, the model has no vision capabilities.
What prompt format is recommended?
Alpaca format is recommended, though Mistral format is also supported.