TR

Tri 7B Base

TriGGUF by mradermacherUpdated 2025-09-08
Download on Hugging Face
Parameters7.53B
Context4K
Layers32
Architecturellama
Smallest quant3.0 GB
Quick answer

Tri 7B Base 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).

Tri 7B Base – a 7.53B parameter transformer foundation model

Tri 7B Base is a 7.53B parameter causal language model with a 4,096 token context length. It is pre‑trained on Korean, English, and Japanese data and serves as the foundation for downstream fine‑tuning and instruction tuning. The model is released under the Apache‑2.0 license.

Good at

  • Efficient pre‑training foundation
  • Supports Korean, English, Japanese
  • Suitable for fine‑tuning

Limits

  • No instruction tuning or alignment
  • Limited to 4,096 token context
  • Requires 8,000 token context for memory estimates

Best for

  • Fine‑tuning domain models
  • Instruction tuning for chat assistants
  • Research on transformer behavior

Who it’s for. Researchers and developers who need a lightweight base model for custom fine‑tuning or instruction tuning. The model is ideal for building specialized language applications in Korean, English, or Japanese.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 5.6 GB
Fits Get file →
Q3_K_S3.4 GB 6.1 GB
Fits Get file →
Q3_K_M3.8 GB 6.4 GB
Fits Get file →
Q3_K_L4.1 GB 6.7 GB
Fits Get file →
IQ4_XS4.2 GB 6.8 GB
Fits Get file →
Q4_K_S4.4 GB 7.1 GB
Fits Get file →
Q4_K_M4.6 GB 7.3 GB
Tight Get file →
Q5_K_S5.2 GB 7.9 GB
Tight Get file →
Q5_K_M5.4 GB 8.0 GB
Too big Get file →
Q6_K6.2 GB 8.8 GB
Too big Get file →
Q8_08.0 GB 10.6 GB
Too big Get file →
F1615.1 GB 17.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (2.99 GB, 7.8 GB memory) or Q3_K_S (3.45 GB, 8.2 GB memory). If 12 GB VRAM is available, Q4_K_M (4.63 GB, 9.4 GB memory) or Q5_K_M (5.38 GB, 10.2 GB memory) are suitable. Higher precision quants such as Q8_0 or F16 require more than 12 GB VRAM.

What GPU do you need for Tri 7B Base?

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 Base quant should you choose?

Q4_K_M is the usual starting point for Tri 7B Base: 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

Architecturellama
Parameters7.53B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyTri
Licenseapache-2.0
Downloads (HF)672
Last updated2025-09-08

Frequently asked questions about Tri 7B Base

How much VRAM does Tri 7B Base 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 Base 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 Base 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 Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Tri 7B Base GGUF?

The files are on Hugging Face in the mradermacher/Tri-7B-Base-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 Base 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 Base on 8 GB VRAM?

Yes, the Q2_K quant uses 2.99 GB and requires approximately 7.8 GB VRAM at 8,000 token context.

Does Tri 7B Base support vision tasks?

No, it is a purely text‑based causal language model with no vision capability.

What languages does Tri 7B Base perform best in?

It is optimized for Korean, English, and Japanese; performance may degrade on other languages.

Other GGUFs of Tri-7B-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Tri models

All Tri →

Other small models

All small models →