Harmonia 20B i1 needs about 23.1 GB of memory at Q4_K_M (a 12.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 19 quants, from 4.6 GB (IQ1_S) to 16.6 GB (Q6_K).
Harmonia 20B i1 – a 20B unified base model
Harmonia 20B i1 is a 20B llama architecture model trained on 4096 context tokens. It is a unified base model created by merging eight 20B models. The model is released under cc‑by‑nc‑4.0 license.
Good at
- Versatile base for TaskArithmetic
- High‑quality writing
- Situational problem‑solving
Limits
- No vision support
- License restricts commercial use
- Requires large VRAM for full precision
Best for
- Research prototyping
- Custom fine‑tuning
- Educational demonstrations
Who it’s for. Developers and researchers who need a large, versatile language model for experimentation and fine‑tuning. The model is suitable for non‑commercial projects due to its cc‑by‑nc‑4.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.6 GB | 10.3 GB | Too big | Get file → | |
| IQ2_XXS | 5.6 GB | 11.3 GB | Too big | Get file → | |
| IQ2_XS | 6.2 GB | 11.9 GB | Too big | Get file → | |
| IQ2_S | 6.6 GB | 12.3 GB | Too big | Get file → | |
| IQ2_M | 7.1 GB | 12.8 GB | Too big | Get file → | |
| Q2_K | 7.6 GB | 13.3 GB | Too big | Get file → | |
| IQ3_XXS | 7.8 GB | 13.5 GB | Too big | Get file → | |
| IQ3_XS | 8.4 GB | 14.1 GB | Too big | Get file → | |
| IQ3_S | 8.9 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_S | 8.9 GB | 14.6 GB | Too big | Get file → | |
| IQ3_M | 9.3 GB | 15.1 GB | Too big | Get file → | |
| Q3_K_M | 9.9 GB | 15.6 GB | Too big | Get file → | |
| Q3_K_L | 10.8 GB | 16.5 GB | Too big | Get file → | |
| IQ4_XS | 10.9 GB | 16.6 GB | Too big | Get file → | |
| Q4_K_S | 11.6 GB | 17.3 GB | Too big | Get file → | |
| Q4_K_M | 12.2 GB | 17.9 GB | Too big | Get file → | |
| Q5_K_S | 14.0 GB | 19.7 GB | Too big | Get file → | |
| Q5_K_M | 14.4 GB | 20.1 GB | Too big | Get file → | |
| Q6_K | 16.6 GB | 22.3 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (4.61 GB, 15.5 GB memory at 8k context). For 12 GB VRAM use Q4_K_M (12.24 GB, 23.1 GB memory). For 16 GB VRAM use Q5_K_M (14.35 GB, 25.3 GB memory). Estimates are approximate.
What GPU do you need for Harmonia 20B 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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ1_S (4.6 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (12.2 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (16.6 GB file, about 27.5 GB in use).
Which Harmonia 20B i1 quant should you choose?
Q4_K_M is the usual starting point for Harmonia 20B i1: it balances file size and quality well. Here it is a 12.2 GB file.
If memory is tight, the smallest file is IQ1_S at 4.6 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
Source
Frequently asked questions about Harmonia 20B i1
How much VRAM does Harmonia 20B i1 need?
About 23.1 GB at Q4_K_M with an 8K context window. That is the 12.2 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 Harmonia 20B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Harmonia 20B i1 GGUF?
It depends on the quant: IQ1_S is 4.6 GB, IQ2_XXS is 5.6 GB, IQ2_XS is 6.2 GB, IQ2_S is 6.6 GB, IQ2_M is 7.1 GB, Q2_K is 7.6 GB and 13 more.
What context length does Harmonia 20B 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 10.4 GB at 8K and 5.2 GB at 4K.
Where can I download Harmonia 20B i1 GGUF?
The files are on Hugging Face in the mradermacher/Harmonia-20B-i1-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 Harmonia 20B i1 use?
Hugging Face lists the license as cc-by-nc-4.0. 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 Harmonia 20B i1 on 8 GB VRAM?
Use the IQ1_S quant, which is 4.61 GB and requires about 15.5 GB memory at 8k context.
Is the model suitable for commercial use?
No, the cc‑by‑nc‑4.0 license prohibits commercial use.
Does the model support vision tasks?
No, Harmonia 20B i1 has no vision capability.