Esper 70b needs about 45.4 GB of memory at Q4_K_M (a 42.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 26.3 GB (Q2_K) to 48.3 GB (Q5_K_S).
Esper 70b – a 70B Llama model focused on DevOps code generation
Esper 70b is a 70B parameter Llama model fine‑tuned for DevOps scripting, Terraform, Dockerfiles, and YAML. It builds on CodeLlama‑70b‑Instruct‑hf and includes additional code‑instruct and chat‑instruct data for improved code quality. The model is released under the apache‑2.0 license.
Good at
- DevOps scripting
- Terraform and Dockerfile generation
- High‑quality code instruction
Limits
- No vision support
- Requires 8.3k context length
- Large VRAM needed for full precision
Best for
- Automating infrastructure scripts
- Generating CI/CD pipelines
- Writing configuration files
Who it’s for. Developers and DevOps engineers who need a specialized code assistant. The model is suitable for teams looking to automate scripting tasks and improve code quality in infrastructure projects.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 26.3 GB | 28.1 GB | Too big | Get file → | |
| IQ3_XS | 29.1 GB | 31.0 GB | Too big | Get file → | |
| IQ3_S | 30.8 GB | 32.6 GB | Too big | Get file → | |
| Q3_K_S | 30.8 GB | 32.6 GB | Too big | Get file → | |
| IQ3_M | 31.8 GB | 33.6 GB | Too big | Get file → | |
| Q3_K_M | 34.1 GB | 36.0 GB | Too big | Get file → | |
| Q3_K_L | 37.0 GB | 38.8 GB | Too big | Get file → | |
| IQ4_XS | 38.0 GB | 39.9 GB | Too big | Get file → | |
| Q4_K_S | 40.1 GB | 41.9 GB | Too big | Get file → | |
| Q4_K_M | 42.3 GB | 44.1 GB | Too big | Get file → | |
| Q5_K_S | 48.3 GB | 50.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (26.3 GB file, 29.5 GB memory at 8k context). For 12 GB VRAM, IQ3_XS (29.15 GB file, 32.3 GB memory) or Q3_K_S (30.75 GB file, 33.9 GB memory). For 16 GB VRAM, Q4_K_M (42.26 GB file, 45.4 GB memory) or Q5_K_S (48.3 GB file, 51.5 GB memory). Estimates are approximate.
What GPU do you need for Esper 70b?
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q2_K (26.3 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (42.3 GB file, about 45.4 GB in use).
Which Esper 70b quant should you choose?
Q4_K_M is the usual starting point for Esper 70b: it balances file size and quality well. Here it is a 42.3 GB file.
If memory is tight, the smallest file is Q2_K at 26.3 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 Esper 70b
How much VRAM does Esper 70b need?
About 45.4 GB at Q4_K_M with an 8K context window. That is the 42.3 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 Esper 70b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Esper 70b GGUF?
It depends on the quant: Q2_K is 26.3 GB, IQ3_XS is 29.1 GB, IQ3_S is 30.8 GB, Q3_K_S is 30.8 GB, IQ3_M is 31.8 GB, Q3_K_M is 34.1 GB and 5 more.
What context length does Esper 70b 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 Esper 70b GGUF?
The files are on Hugging Face in the mradermacher/Esper-70b-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 Esper 70b 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 Esper 70b on 8 GB VRAM?
The smallest quant, Q2_K, requires about 29.5 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
Does Esper 70b support vision tasks?
No, the model has no vision capability.