Holgerim Llama 7b i1 needs about 8.6 GB of memory at Q4_K_M (a 4.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.5 GB (IQ1_S) to 5.4 GB (Q6_K).
Holgerim Llama 7b i1 – a 6.54B Llama model merged with SLERP
Holgerim Llama 7b i1 is a 6.54B parameter Llama model merged using SLERP. It supports a 4096 token context and is available in a variety of GGUF quantizations. The model is built from Canarim-7B-Instruct and Holger-7B-v0.1.
Good at
- Instruct-style dialogue
- Text generation
- Language modeling
Limits
- No vision support
- License not specified
- Context limited to 4096 tokens
Best for
- Chatbot prototypes
- Content drafting
- Code generation
Who it’s for. Developers and researchers who need a lightweight Llama model for local inference. The model is suitable for users with moderate GPU memory who prefer GGUF quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.5 GB | 4.1 GB | Fits | Get file → | |
| IQ1_M | 1.6 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XXS | 1.8 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XS | 2.0 GB | 4.6 GB | Fits | Get file → | |
| IQ2_S | 2.1 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_S | 2.2 GB | 4.8 GB | Fits | Get file → | |
| IQ2_M | 2.3 GB | 4.9 GB | Fits | Get file → | |
| Q2_K | 2.5 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 2.5 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XS | 2.7 GB | 5.3 GB | Fits | Get file → | |
| IQ3_S | 2.9 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 2.9 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 3.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 3.2 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 3.5 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 3.5 GB | 6.1 GB | Fits | Get file → | |
| IQ4_NL | 3.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 3.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_S | 3.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.0 GB | 6.5 GB | Fits | Get file → | |
| Q4_1 | 4.1 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_S | 4.5 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_M | 4.6 GB | 7.2 GB | Tight | Get file → | |
| Q6_K | 5.4 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM, use IQ1_S (1.48 GB, 6.1 GB memory at 8k context) or IQ1_M (1.6 GB, 6.3 GB). If you have 12 GB VRAM, Q4_K_M (3.95 GB, 8.6 GB) or Q5_K_M (4.64 GB, 9.3 GB) are good choices. Larger VRAM allows Q6_K (5.36 GB, 10 GB).
What GPU do you need for Holgerim Llama 7b 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: the best quant that fits is Q3_K_M (3.2 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.4 GB file, about 10.0 GB in use).
Which Holgerim Llama 7b i1 quant should you choose?
Q4_K_M is the usual starting point for Holgerim Llama 7b i1: it balances file size and quality well. Here it is a 4.0 GB file.
If memory is tight, the smallest file is IQ1_S at 1.5 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 Holgerim Llama 7b i1
How much VRAM does Holgerim Llama 7b i1 need?
About 8.6 GB at Q4_K_M with an 8K context window. That is the 4.0 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 Holgerim Llama 7b i1 on an 8 GB GPU?
Yes, with Q3_K_M: the 3.2 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 Holgerim Llama 7b i1 GGUF?
It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.6 GB, IQ2_XXS is 1.8 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.1 GB, Q2_K_S is 2.2 GB and 18 more.
What context length does Holgerim Llama 7b 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 4.2 GB at 8K and 2.1 GB at 4K.
Where can I download Holgerim Llama 7b i1 GGUF?
The files are on Hugging Face in the mradermacher/Holgerim-Llama-7b-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 Holgerim Llama 7b i1 on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations; they require about 6.1–6.3 GB memory at 8k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length?
The model supports up to 4096 tokens.