Tri 7B needs about 9.4 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 3.0 GB (Q2_K) to 15.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.
Tri 7B – 7.53B parameter Llama model with 32K context
Tri 7B is a 7.53B parameter causal language model built on the Llama architecture. It supports a context length of 32768 tokens and is optimized for English, Korean, and Japanese. The model is released under the Apache‑2.0 license.
Good at
- Reasoning tasks
- Mathematical reasoning
- Instruction following
Limits
- No vision support
- Limited to English, Korean, Japanese
- Requires 8K context for memory estimates
Best for
- Long‑form text generation
- Chat applications
- Coding assistance
Who it’s for. Developers and researchers needing a compact yet capable Llama‑style model for text‑only workloads. The model is suitable for local deployment with GGUF support via llama.cpp, vLLM, or SGLang.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.0 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_S | 3.4 GB | 8.2 GB | Too big | Get file → | |
| Q3_K_M | 3.8 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_L | 4.1 GB | 8.9 GB | Too big | Get file → | |
| IQ4_XS | 4.2 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_S | 4.4 GB | 9.2 GB | Too big | Get file → | |
| Q4_K_M | 4.6 GB | 9.4 GB | Too big | Get file → | |
| Q5_K_S | 5.3 GB | 10.0 GB | Too big | Get file → | |
| Q5_K_M | 5.4 GB | 10.2 GB | Too big | Get file → | |
| Q6_K | 6.2 GB | 11.0 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 12.8 GB | Too big | Get file → | |
| F16 | 15.1 GB | 19.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (file size 4.41 GB, estimated 9.2 GB memory). For 12 GB VRAM, Q6_K (6.18 GB, 11 GB memory) or Q5_K_M (5.38 GB, 10.2 GB memory) are suitable. For 16 GB VRAM, Q8_0 (8 GB, 12.8 GB memory) or F16 (15.06 GB, 19.9 GB memory) provide higher precision.
What GPU do you need for Tri 7B?
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 Q2_K (3.0 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 11.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 12.8 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.1 GB file, about 19.9 GB in use).
Which Tri 7B quant should you choose?
Q4_K_M is the usual starting point for Tri 7B: it balances file size and quality well. Here it is a 4.6 GB file.
The Q8_0 file is 8.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.0 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 Tri 7B
How much VRAM does Tri 7B need?
About 9.4 GB at Q4_K_M with an 8K context window. That is the 4.6 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 Tri 7B on an 8 GB GPU?
Yes, with Q2_K: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Tri 7B GGUF?
It depends on the quant: Q2_K is 3.0 GB, Q3_K_S is 3.4 GB, Q3_K_M is 3.8 GB, Q3_K_L is 4.1 GB, IQ4_XS is 4.2 GB, Q4_K_S is 4.4 GB and 6 more.
What context length does Tri 7B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.
Where can I download Tri 7B GGUF?
The files are on Hugging Face in the mradermacher/Tri-7B-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 Tri 7B 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 Tri 7B on 8 GB VRAM?
Yes, using the Q4_K_S quantized file (4.41 GB) will fit within 8 GB VRAM with an estimated 9.2 GB memory usage.
Does Tri 7B support image inputs?
No, Tri 7B is a text‑only model and does not have vision capabilities.
What languages is Tri 7B optimized for?
Tri 7B is specifically optimized for English, Korean, and Japanese; other languages may perform less well.