johnpaulbin e2 instruct merge needs about 16.3 GB of memory at Q4_K_M (a 14.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 14.6 GB (Q2_K) to 15.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
4.54B llama model merged with instruct capabilities
johnpaulbin-e2 instruct merge is a 4.54B parameter llama model. It merges johnpaulbin/llama3.1-8b-e2-epoch3-merged-fp16 and unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit. The model supports 131072 token context and is available in multiple GGUF quantizations.
Good at
- Instruct style dialogue
- Large context handling
- Low‑precision inference
Limits
- No vision support
- License not specified
- Requires high VRAM for full precision
Best for
- Chatbot development
- Fine‑tuning on custom data
- Local inference with llama.cpp
Who it’s for. Developers and researchers who need a merged instruct model with a large context window. The model is suitable for local deployment using llama.cpp and similar inference engines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 14.6 GB | 16.1 GB | Too big | Get file → | |
| IQ3_M | 14.6 GB | 16.2 GB | Too big | Get file → | |
| IQ3_S | 14.6 GB | 16.2 GB | Too big | Get file → | |
| IQ3_XS | 14.6 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_M | 14.6 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_S | 14.6 GB | 16.2 GB | Too big | Get file → | |
| IQ4_XS | 14.7 GB | 16.3 GB | Too big | Get file → | |
| Q4_K_M | 14.7 GB | 16.3 GB | Too big | Get file → | |
| Q4_K_S | 14.7 GB | 16.3 GB | Too big | Get file → | |
| Q5_K_M | 14.8 GB | 16.3 GB | Too big | Get file → | |
| Q5_K_S | 14.8 GB | 16.3 GB | Too big | Get file → | |
| Q6_K | 14.8 GB | 16.4 GB | Too big | Get file → | |
| Q8_0 | 15.1 GB | 16.7 GB | Too big | Get file → |
For 8GB VRAM the smallest quant is Q2_K, but it requires approximately 16.1GB memory at 8k context, so it is not suitable. With 16GB VRAM use Q2_K or Q3_K_M. For 32GB VRAM use Q4_K_M or Q5_K_M for better quality.
What GPU do you need for johnpaulbin e2 instruct merge?
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 Q8_0 (15.1 GB file, about 16.7 GB in use).
Which johnpaulbin e2 instruct merge quant should you choose?
Q4_K_M is the usual starting point for johnpaulbin e2 instruct merge: it balances file size and quality well. Here it is a 14.7 GB file.
The Q8_0 file is 15.1 GB, about 1.0 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 14.6 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
Frequently asked questions about johnpaulbin e2 instruct merge
How much VRAM does johnpaulbin e2 instruct merge need?
About 16.3 GB at Q4_K_M with an 8K context window. That is the 14.7 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 johnpaulbin e2 instruct merge on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of johnpaulbin e2 instruct merge GGUF?
It depends on the quant: Q2_K is 14.6 GB, IQ3_M is 14.6 GB, IQ3_S is 14.6 GB, IQ3_XS is 14.6 GB, Q3_K_L is 14.6 GB, Q3_K_M is 14.6 GB and 8 more.
What context length does johnpaulbin e2 instruct merge support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download johnpaulbin e2 instruct merge GGUF?
The files are on Hugging Face in the mradermacher/johnpaulbin-e2-instruct-merge-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 8GB VRAM?
No, the smallest quant requires about 16.1GB memory at 8k context, so 8GB VRAM is insufficient.
Does it support vision?
No, the model has no vision capabilities.
Can I use it with llama.cpp?
Yes, the GGUF files are compatible with llama.cpp.