Llama3-UmbralMind-v1-15M needs about 11.8 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 3.5 GB (IQ1_S) to 12.3 GB (Q6_K).
15B‑parameter Llama3 model focused on roleplay
Llama3-UmbralMind-v1-15M is a 15‑billion‑parameter Llama model merged from four copies of L3‑Umbral‑Mind‑RP‑v1.0‑8B. It supports a 8192‑token context window and is available in multiple GGUF quantizations. The model is tailored for role‑playing scenarios.
Good at
- Role‑play conversations
- Text generation with 8192‑token context
- Customizable quantization
Limits
- No vision support
- License not specified
- Large memory requirement for high‑quality quants
Best for
- Chatbot role‑play scripts
- Interactive storytelling
- Custom LLM demos
Who it’s for. Developers and researchers who need a large Llama model for role‑playing tasks and can manage the memory demands of high‑quality quantizations. The model is suitable for local deployment with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.5 GB | 6.1 GB | Fits | Get file → | |
| IQ1_M | 3.8 GB | 6.4 GB | Fits | Get file → | |
| IQ2_XXS | 4.3 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XS | 4.7 GB | 7.3 GB | Tight | Get file → | |
| IQ2_S | 4.9 GB | 7.6 GB | Tight | Get file → | |
| IQ2_M | 5.3 GB | 7.9 GB | Tight | Get file → | |
| Q2_K | 5.7 GB | 8.4 GB | Too big | Get file → | |
| IQ3_XXS | 6.0 GB | 8.6 GB | Too big | Get file → | |
| IQ3_XS | 6.4 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_S | 6.7 GB | 9.3 GB | Too big | Get file → | |
| IQ3_S | 6.7 GB | 9.3 GB | Too big | Get file → | |
| IQ3_M | 6.9 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_M | 7.4 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_L | 8.0 GB | 10.6 GB | Too big | Get file → | |
| IQ4_XS | 8.2 GB | 10.8 GB | Too big | Get file → | |
| Q4_0 | 8.6 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_S | 8.6 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_M | 9.1 GB | 11.8 GB | Too big | Get file → | |
| Q5_K_S | 10.4 GB | 13.0 GB | Too big | Get file → | |
| Q5_K_M | 10.7 GB | 13.3 GB | Too big | Get file → | |
| Q6_K | 12.3 GB | 15.0 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (file size 3.5 GB, memory 6.1 GB). For 12‑GB VRAM, IQ2_M (5.3 GB, 7.9 GB) or Q3_K_M (7.37 GB, 10 GB). For 16‑GB VRAM, Q4_K_M (9.11 GB, 11.8 GB) or Q5_K_S (10.4 GB, 13 GB). Memory estimates are approximate.
What GPU do you need for Llama3-UmbralMind-v1-15M?
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 IQ2_M (5.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (9.1 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 15.0 GB in use).
Which Llama3-UmbralMind-v1-15M quant should you choose?
Q4_K_M is the usual starting point for Llama3-UmbralMind-v1-15M: it balances file size and quality well. Here it is a 9.1 GB file.
If memory is tight, the smallest file is IQ1_S at 3.5 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 Llama3-UmbralMind-v1-15M
How much VRAM does Llama3-UmbralMind-v1-15M need?
About 11.8 GB at Q4_K_M with an 8K context window. That is the 9.1 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 Llama3-UmbralMind-v1-15M on an 8 GB GPU?
Yes, with IQ2_M: the 5.3 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 Llama3-UmbralMind-v1-15M GGUF?
It depends on the quant: IQ1_S is 3.5 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 4.9 GB, IQ2_M is 5.3 GB and 15 more.
What context length does Llama3-UmbralMind-v1-15M support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.
Where can I download Llama3-UmbralMind-v1-15M GGUF?
The files are on Hugging Face in the mradermacher/Llama3-UmbralMind-v1-15M-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 this model on 8 GB VRAM?
Yes, the IQ1_S quant uses about 6.1 GB of VRAM at 8k context, which fits within an 8 GB GPU.
Does the model support vision?
No, the model has no vision capabilities.
What is the context length?
The model supports a 8192‑token context window.