lzlv limarpv3 l2 70b 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).
Llama 2‑based 70B model merged with LimaRP v3 adapter
This 70B Llama 2 model merges lizpreciatior/lzlv_70b_fp16_hf with a PEFT adapter trained on LimaRP v3. It uses the Alpaca instruction format and supports length modifiers such as micro, tiny, short, medium, long, massive, huge, enormous, humongous, unlimited.
Good at
- Role‑playing with length control
- Custom prompt formatting
- Large context handling
Limits
- No vision support
- Not for factual advice
- Requires 8k context for estimates
Best for
- Interactive storytelling
- Custom instruction generation
- Long‑form content creation
Who it’s for. Developers and researchers needing a large Llama 2 model with LimaRP v3 style prompts. Suitable for applications that can handle a 70B parameter model and require custom length control in responses.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 14.9 GB | 16.7 GB | Too big | Get file → | |
| IQ1_M | 15.9 GB | 17.8 GB | Too big | Get file → | |
| IQ2_XXS | 18.6 GB | 20.5 GB | Too big | Get file → | |
| IQ2_XS | 20.7 GB | 22.5 GB | Too big | Get file → | |
| IQ2_S | 21.7 GB | 23.5 GB | Too big | Get file → | |
| IQ2_M | 23.6 GB | 25.4 GB | Too big | Get file → | |
| Q2_K | 25.8 GB | 27.6 GB | Too big | Get file → | |
| IQ3_XXS | 27.3 GB | 29.2 GB | Too big | Get file → | |
| IQ3_XS | 28.5 GB | 30.3 GB | Too big | Get file → | |
| Q3_K_XS | 28.6 GB | 30.4 GB | Too big | Get file → | |
| IQ3_S | 30.2 GB | 32.1 GB | Too big | Get file → | |
| Q3_K_S | 30.2 GB | 32.1 GB | Too big | Get file → | |
| IQ3_M | 31.3 GB | 33.1 GB | Too big | Get file → | |
| Q3_K_M | 33.6 GB | 35.4 GB | Too big | Get file → | |
| Q3_K_L | 36.5 GB | 38.3 GB | Too big | Get file → | |
| IQ4_XS | 37.1 GB | 39.0 GB | Too big | Get file → | |
| Q4_0 | 39.0 GB | 40.9 GB | Too big | Get file → | |
| Q4_K_S | 39.6 GB | 41.4 GB | Too big | Get file → | |
| Q4_K_M | 41.7 GB | 43.6 GB | Too big | Get file → | |
| Q5_K_S | 47.8 GB | 49.6 GB | Too big | Get file → | |
| Q5_K_M | 49.1 GB | 50.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (14.88 GB file, 18.1 GB memory at 8k context). For 12 GB VRAM, IQ1_M (15.94 GB file, 19.1 GB memory). For 16 GB VRAM, IQ2_XXS (18.63 GB file, 21.8 GB memory).
What GPU do you need for lzlv limarpv3 l2 70b 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 Q3_K_XS (28.6 GB file, about 31.7 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 lzlv limarpv3 l2 70b i1 quant should you choose?
Q4_K_M is the usual starting point for lzlv limarpv3 l2 70b 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 lzlv limarpv3 l2 70b i1
How much VRAM does lzlv limarpv3 l2 70b 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 lzlv limarpv3 l2 70b 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 lzlv limarpv3 l2 70b 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 lzlv limarpv3 l2 70b i1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download lzlv limarpv3 l2 70b i1 GGUF?
The files are on Hugging Face in the mradermacher/lzlv-limarpv3-l2-70b-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 18.1 GB memory at 8k context, which exceeds 8 GB VRAM, so it is not feasible without off‑loading.
What context length does this model support?
The model was trained with 4096 tokens and can handle up to that context length.
Does this model support vision?
No, the model has no vision capabilities.