Sumo T9 7B v0.1 i1 needs about 8.7 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.7 GB (IQ1_S) to 5.7 GB (Q6_K).
Sumo T9 7B v0.1 i1 – 6.9B Llama‑style model for Bittensor Subnet 9
Sumo T9 7B v0.1 i1 is a 6.9B parameter Llama‑style pretrained model released under the MIT license. It is trained on the tiiuae/falcon‑refinedweb dataset and supports a 4096 token context window. The model is unaligned and should be fine‑tuned before deployment.
Good at
- Large context handling
- English‑centric NLP tasks
- Decentralized network training
Limits
- Unaligned, use with caution
- No vision support
- Requires fine‑tuning for production
Best for
- Research prototyping
- Fine‑tuning for downstream tasks
- Benchmarking on Bittensor Subnet 9
Who it’s for. Researchers and developers working with Llama‑style models who need a 7B parameter base model for fine‑tuning or benchmarking. The model is suitable for those who prefer open‑source, MIT‑licensed models and have access to GPU resources for inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.7 GB | 4.2 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 4.5 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 4.7 GB | Fits | Get file → | |
| IQ2_S | 2.4 GB | 4.9 GB | Fits | Get file → | |
| Q2_K_S | 2.5 GB | 5.0 GB | Fits | Get file → | |
| IQ2_M | 2.5 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XS | 3.0 GB | 5.5 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 5.6 GB | Fits | Get file → | |
| IQ3_M | 3.3 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 3.4 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_L | 3.7 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 3.8 GB | 6.3 GB | Fits | Get file → | |
| IQ4_NL | 4.0 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 4.0 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 4.0 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 4.2 GB | 6.7 GB | Fits | Get file → | |
| Q4_1 | 4.4 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_S | 4.8 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_M | 4.9 GB | 7.4 GB | Tight | Get file → | |
| Q6_K | 5.7 GB | 8.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S or IQ1_M (file size 1.72 GB or 1.84 GB, memory ~6.3–6.4 GB). For 12 GB VRAM, IQ2_S or Q2_K_S (file size 2.38 GB or 2.5 GB, memory ~6.9–7 GB). For 24 GB VRAM, Q5_K_M or Q6_K (file size 4.91 GB or 5.66 GB, memory ~9.4–10.2 GB).
What GPU do you need for Sumo T9 7B v0.1 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: the best quant that fits is Q3_K_M (3.4 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.2 GB in use).
Which Sumo T9 7B v0.1 i1 quant should you choose?
Q4_K_M is the usual starting point for Sumo T9 7B v0.1 i1: it balances file size and quality well. Here it is a 4.2 GB file.
If memory is tight, the smallest file is IQ1_S at 1.7 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 Sumo T9 7B v0.1 i1
How much VRAM does Sumo T9 7B v0.1 i1 need?
About 8.7 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Sumo T9 7B v0.1 i1 on an 8 GB GPU?
Yes, with Q3_K_M: the 3.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sumo T9 7B v0.1 i1 GGUF?
It depends on the quant: IQ1_S is 1.7 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.4 GB, Q2_K_S is 2.5 GB and 18 more.
What context length does Sumo T9 7B v0.1 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 4.0 GB at 8K and 2.0 GB at 4K.
Where can I download Sumo T9 7B v0.1 i1 GGUF?
The files are on Hugging Face in the mradermacher/Sumo-T9-7B-v0.1-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 Sumo T9 7B v0.1 i1 use?
Hugging Face lists the license as mit. 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 Sumo T9 7B v0.1 i1 on 8 GB VRAM?
Yes, use the IQ1_S or IQ1_M quant, which require about 6.3–6.4 GB of VRAM at 8K context.
Does this model support vision tasks?
No, the model is a text‑only Llama‑style model and does not include vision capabilities.
Is the model aligned for safe use?
No, the model is unaligned. It should be fine‑tuned or used with caution for downstream applications.