Mini Lama 8B Base needs about 6.8 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Mini Lama 8B Base – 8.49B parameter Llama model with vision capability
Mini Lama 8B Base is a 8.49B parameter Llama model trained on 262144 context tokens. It is released under the apache-2.0 license and includes vision support. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- Vision integration
- Flexible quant options
Limits
- High VRAM requirement for larger quants
- No official vision API integration
- Requires custom tokenizer checksum for llama.cpp
Best for
- Vision‑enabled text generation
- Fine‑tuning on custom datasets
- Low‑latency inference on mid‑range GPUs
Who it’s for. Developers and researchers needing a versatile Llama model with vision support and a range of quantization options. The model is suitable for experimentation and production use where custom tokenizer handling is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ1_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ2_XXS | 2.5 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XS | 2.7 GB | 4.4 GB | Fits | Get file → | |
| IQ2_S | 2.9 GB | 4.5 GB | Fits | Get file → | |
| IQ2_M | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_S | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q2_K | 3.4 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.5 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ3_S | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 4.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_L | 4.6 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 4.9 GB | 6.6 GB | Fits | Get file → | |
| IQ4_NL | 4.9 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_S | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_M | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_1 | 5.4 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_S | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_M | 6.1 GB | 7.7 GB | Tight | Get file → | |
| Q6_K | 7.0 GB | 8.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 4.94 GB, memory 6.6 GB at 8 k context). For 12 GB VRAM, Q5_K_M (file size 6.06 GB, memory 7.7 GB) or Q6_K (file size 6.97 GB, memory 8.6 GB). Larger VRAM allows higher‑quality quants such as Q6_K.
What GPU do you need for Mini Lama 8B Base?
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: the best quant that fits is IQ1_M (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.2 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 8.6 GB in use).
Which Mini Lama 8B Base quant should you choose?
Q4_K_M is the usual starting point for Mini Lama 8B Base: it balances file size and quality well. Here it is a 5.2 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 Mini Lama 8B Base
How much VRAM does Mini Lama 8B Base need?
About 6.8 GB at Q4_K_M with an 8K context window. That is the 5.2 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 Mini Lama 8B Base on an 8 GB GPU?
Yes, with Q5_K_M: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mini Lama 8B Base GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.
What context length does Mini Lama 8B Base support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Mini Lama 8B Base GGUF?
The files are on Hugging Face in the mradermacher/Mini-Lama-8B-Base-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 Mini Lama 8B Base 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.
Can I run Mini Lama 8B Base on 8 GB VRAM?
Yes, the Q4_0 quant uses about 6.6 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does this model work with llama.cpp?
Yes, but the tokenizer requires adding its checksum to convert_hf_to_gguf.py before conversion.
Is vision support available out of the box?
The model has vision tokens, but llama.cpp does not provide a built‑in vision API; custom handling is needed.