LEMA Llama 2 7b needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 5.5 GB (Q6_K).
LEMA Llama 2 7b – fine‑tuned Llama‑2‑7b with LEMA memory virtualization
LEMA Llama 2 7b is a 6.74B‑parameter Llama model fine‑tuned with LoRA rank 16, alpha 32. It uses the LEMA framework to virtualize GPU memory, allowing training on 16GB VRAM. The model is released under the MIT license.
Good at
- Efficient VRAM usage
- LoRA fine‑tuning
- Custom chat format support
Limits
- No vision support
- Training limited to 1 epoch
- Requires GPU for inference
Best for
- Low‑VRAM inference
- Rapid LoRA prototyping
- Custom chat format testing
Who it’s for. Developers and researchers who need to run or fine‑tune a 7B Llama model on consumer‑grade GPUs with limited VRAM. The model is suitable for proof‑of‑concept experiments and low‑resource deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| IQ1_S | 1.5 GB | 4.2 GB | Fits | Get file → | |
| IQ1_M | 1.7 GB | 4.3 GB | Fits | Get file → | |
| IQ2_XXS | 1.9 GB | 4.5 GB | Fits | Get file → | |
| IQ2_XS | 2.0 GB | 4.7 GB | Fits | Get file → | |
| IQ2_S | 2.2 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_S | 2.3 GB | 5.0 GB | Fits | Get file → | |
| IQ2_M | 2.4 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 2.5 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 2.6 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XS | 2.8 GB | 5.4 GB | Fits | Get file → | |
| IQ3_S | 2.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_S | 2.9 GB | 5.6 GB | Fits | Get file → | |
| IQ3_M | 3.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 3.3 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_L | 3.6 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 3.6 GB | 6.3 GB | Fits | Get file → | |
| IQ4_NL | 3.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 3.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 3.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 6.7 GB | Fits | Get file → | |
| Q4_1 | 4.2 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_S | 4.7 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_M | 4.8 GB | 7.4 GB | Tight | Get file → | |
| Q6_K | 5.5 GB | 8.2 GB | Too big | Get file → |
For 8GB VRAM, the Q4_K_M quant (~4.08 GB file, 8.9 GB memory at 8k context) is a good balance. If more memory is available, Q5_K_M (~4.78 GB file, 9.6 GB memory) offers higher quality. For tighter budgets, IQ1_S (~1.53 GB file, 6.3 GB memory) is the smallest option.
What GPU do you need for LEMA Llama 2 7b?
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: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).
Which LEMA Llama 2 7b quant should you choose?
Q4_K_M is the usual starting point for LEMA Llama 2 7b: it balances file size and quality well. Here it is a 4.1 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 LEMA Llama 2 7b
How much VRAM does LEMA Llama 2 7b need?
About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 LEMA Llama 2 7b on an 8 GB GPU?
Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LEMA Llama 2 7b GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB and 19 more.
What context length does LEMA Llama 2 7b support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download LEMA Llama 2 7b GGUF?
The files are on Hugging Face in the mradermacher/LEMA-llama-2-7b-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 LEMA Llama 2 7b use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run LEMA Llama 2 7b on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 8.9 GB of VRAM at 8k context, which fits within an 8 GB GPU with some headroom.
What is the best quant for low‑memory GPUs?
IQ1_S is the smallest quant at 1.53 GB file size and 6.3 GB memory usage, suitable for GPUs with limited VRAM.
Does this model support vision tasks?
No, the model has no vision capabilities and is text‑only.