Dolphin Email 8b v2 needs about 7.3 GB of memory at Q5_K_M (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Dolphin Email 8b v2 – a local 8B model for safe email drafting
Dolphin Email 8b v2 is a 8.03 B parameter model fine‑tuned for email writing. It never invents concrete facts and outputs placeholders for missing data. The model is built on Dolphin3.0‑Llama3.1‑8B and is available in Q5_K_M quantized GGUF format.
Good at
- Email drafting from brief
- Fact‑safe placeholders
- Reply in‑thread
Limits
- No vision support
- Requires 8 k context for memory estimate
- License is llama3.1
Best for
- Writing professional emails
- Drafting replies with placeholders
- Generating email templates
Who it’s for. Developers and businesses that need a local, controllable model for email generation. The model allows setting system prompts and alignment without external data collection.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 5.7 GB | 7.3 GB | Tight | Get file → |
For 8 GB VRAM, use Q5_K_M (5.73 GB file, ~7.3 GB memory at 8 k context). If more VRAM is available, a higher‑precision quant could be used, but Q5_K_M is the only quant in the repo.
What GPU do you need for Dolphin Email 8b v2?
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 Q5_K_M (5.7 GB file, about 7.3 GB in use).
Which Dolphin Email 8b v2 quant should you choose?
Q5_K_M (5.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Dolphin Email 8b v2
How much VRAM does Dolphin Email 8b v2 need?
About 7.3 GB at Q5_K_M with an 8K context window. That is the 5.7 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 Dolphin Email 8b v2 on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Dolphin Email 8b v2 GGUF?
It depends on the quant: Q5_K_M is 5.7 GB.
What context length does Dolphin Email 8b v2 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 Dolphin Email 8b v2 GGUF?
The files are on Hugging Face in the h0ney-badger/dolphin-email-8b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Dolphin Email 8b v2 use?
Hugging Face lists the license as llama3.1. 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 Dolphin Email 8b v2 on 8 GB VRAM?
Yes, the Q5_K_M quant uses about 7.3 GB of VRAM at 8 k context, which fits within 8 GB.
Does the model support image input?
No, the model has no vision capability.
Will the model generate personal data like addresses?
No, it outputs placeholders such as [DATE] or [RECIPIENT EMAIL] instead of invented facts.