Breeze-7B-Instruct-v0_1 needs about 6.1 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 2.9 GB (Q2_K) to 8.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Breeze-7B-Instruct v0.1 – 7B parameter language model for Traditional Chinese and English
Breeze-7B-Instruct v0.1 is a 7B parameter llama architecture model. It supports a 32,768 token context length and is suitable for instruction following tasks. The model is available in multiple GGUF quantizations.
Good at
- Instruction following
- Q&A and summarization
- Multi‑round chat
Limits
- No vision support
- License not specified
- Large memory for higher quantizations
Best for
- Chatbots in Traditional Chinese
- Document‑level Q&A
- Fine‑tuning for specific domains
Who it’s for. Developers and researchers needing a 7B instruction model with Traditional Chinese support. The model is useful for fine‑tuning or direct use in text‑generation pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.9 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XS | 3.2 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_S | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_S | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_M | 3.4 GB | 5.0 GB | Fits | Get file → | |
| Q3_K | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_M | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_L | 4.0 GB | 5.5 GB | Fits | Get file → | |
| IQ4_XS | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 4.3 GB | 5.9 GB | Fits | Get file → | |
| IQ4_NL | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_M | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q4_1 | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q5_0 | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q5_K | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_M | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q5_1 | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q6_K | 6.1 GB | 7.7 GB | Tight | Get file → | |
| Q8_0 | 8.0 GB | 9.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 4.28 GB, memory 5.9 GB). For 12 GB VRAM, Q5_0 (5.18 GB, 6.8 GB) or Q5_K (5.32 GB, 6.9 GB). For 16 GB VRAM, Q6_K (6.14 GB, 7.7 GB) or Q8_0 (7.96 GB, 9.5 GB) are suitable. Estimates are approximate.
What GPU do you need for Breeze-7B-Instruct-v0_1?
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: the best quant that fits is IQ4_NL (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.5 GB in use).
Which Breeze-7B-Instruct-v0_1 quant should you choose?
Q4_K_M is the usual starting point for Breeze-7B-Instruct-v0_1: it balances file size and quality well. Here it is a 4.5 GB file.
The Q8_0 file is 8.0 GB, about 1.8 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 2.9 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
Frequently asked questions about Breeze-7B-Instruct-v0_1
How much VRAM does Breeze-7B-Instruct-v0_1 need?
About 6.1 GB at Q4_K_M with an 8K context window. That is the 4.5 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 Breeze-7B-Instruct-v0_1 on an 8 GB GPU?
Yes, with Q6_K: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Breeze-7B-Instruct-v0_1 GGUF?
It depends on the quant: Q2_K is 2.9 GB, IQ3_XS is 3.2 GB, Q3_K_S is 3.3 GB, IQ3_S is 3.3 GB, IQ3_M is 3.4 GB, Q3_K is 3.7 GB and 16 more.
What context length does Breeze-7B-Instruct-v0_1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Breeze-7B-Instruct-v0_1 GGUF?
The files are on Hugging Face in the RichardErkhov/MediaTek-Research_-_Breeze-7B-Instruct-v0_1-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 Breeze-7B-Instruct on 8 GB VRAM?
Yes, using the Q4_0 quantization which requires about 5.9 GB of VRAM at 8 k context.
Does Breeze-7B-Instruct support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length of Breeze-7B-Instruct?
The model supports 32,768 tokens as its trained context length.