BR

Breeze 7B 32k Instruct V1_0

BreezeGGUF by RichardErkhovUpdated 2024-09-18
Download on Hugging Face
Parameters7.49B
Context32K
Layers32
Architecturellama
Smallest quant2.9 GB
Quick answer

Breeze 7B 32k Instruct V1_0 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 32k Instruct V1_0 – a 7.49B Chinese‑focused instruction model

Breeze 7B 32k Instruct V1_0 is a 7.49B parameter llama‑based model trained on 32,768 token context. It is optimized for Traditional Chinese and supports instruction following, Q&A, RAG, and multi‑round chat.

Good at

  • Instruction following
  • Large context handling
  • Chinese language tasks

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Apache‑2.0 license

Best for

  • Chatbots needing long context
  • Document‑level summarization
  • RAG pipelines

Who it’s for. Developers building Chinese‑centric LLM applications who need a large context window and instruction capability. The model is suitable for fine‑tuning or direct use in inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.9 GB 4.4 GB
Fits Get file →
IQ3_XS3.2 GB 4.7 GB
Fits Get file →
Q3_K_S3.3 GB 4.9 GB
Fits Get file →
IQ3_S3.3 GB 4.9 GB
Fits Get file →
IQ3_M3.4 GB 5.0 GB
Fits Get file →
Q3_K3.7 GB 5.2 GB
Fits Get file →
Q3_K_M3.7 GB 5.2 GB
Fits Get file →
Q3_K_L4.0 GB 5.6 GB
Fits Get file →
IQ4_XS4.1 GB 5.7 GB
Fits Get file →
Q4_04.3 GB 5.9 GB
Fits Get file →
Q4_K_S4.3 GB 5.9 GB
Fits Get file →
IQ4_NL4.3 GB 5.9 GB
Fits Get file →
Q4_K4.5 GB 6.1 GB
Fits Get file →
Q4_K_M4.5 GB 6.1 GB
Fits Get file →
Q4_14.7 GB 6.3 GB
Fits Get file →
Q5_05.2 GB 6.8 GB
Fits Get file →
Q5_K_S5.2 GB 6.8 GB
Fits Get file →
Q5_K5.3 GB 6.9 GB
Fits Get file →
Q5_K_M5.3 GB 6.9 GB
Fits Get file →
Q5_15.6 GB 7.2 GB
Tight Get file →
Q6_K6.1 GB 7.7 GB
Tight Get file →
Q8_08.0 GB 9.5 GB
Too big Get file →

For 8 GB VRAM use Q4_0 (file size 4.28 GB, ~5.9 GB memory). For 12 GB VRAM use Q5_0 (5.19 GB, ~6.8 GB). For 16 GB VRAM use Q6_K (6.15 GB, ~7.7 GB).

What GPU do you need for Breeze 7B 32k Instruct V1_0?

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 32k Instruct V1_0 quant should you choose?

Q4_K_M is the usual starting point for Breeze 7B 32k Instruct V1_0: 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

Architecturellama
Parameters7.49B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyBreeze
Licenseapache-2.0
Downloads (HF)2,954
Last updated2024-09-18

Frequently asked questions about Breeze 7B 32k Instruct V1_0

How much VRAM does Breeze 7B 32k Instruct V1_0 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 32k Instruct V1_0 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 32k Instruct V1_0 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 32k Instruct V1_0 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 32k Instruct V1_0 GGUF?

The files are on Hugging Face in the RichardErkhov/MediaTek-Research_-_Breeze-7B-32k-Instruct-v1_0-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 Breeze 7B 32k Instruct V1_0 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 Breeze 7B 32k Instruct on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 5.9 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Breeze models

All Breeze →

Other small models

All small models →