CH

Chihiro-7B-v0.1

ChihiroGGUF by mradermacherUpdated 2025-01-26
Download on Hugging Face
Parameters7.49B
Context32K
Layers32
Architecturellama
Smallest quant1.7 GB
Quick answer

Chihiro-7B-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 24 quants, from 1.7 GB (IQ1_S) to 6.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Chihiro-7B-v0.1 – a 7.49B llama-based model

Chihiro-7B-v0.1 is a 7.49B parameter llama model. It was created by merging Zebrafish 7B and Breeze 7B using SLERP. The model supports a context length of 32768 tokens.

Good at

  • Large context handling
  • Experimental Mistral architecture
  • Bilingual Chinese support

Limits

  • License unknown
  • No vision support
  • No active parameters listed

Best for

  • Chat applications with long context
  • Research on SLERP merges
  • Chinese language tasks

Who it’s for. Developers and researchers who need a large-context llama model with experimental Mistral architecture. The model is suitable for those who can handle an unknown license and lack vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.7 GB 3.3 GB
Fits Get file →
IQ1_M1.9 GB 3.5 GB
Fits Get file →
IQ2_XXS2.1 GB 3.7 GB
Fits Get file →
IQ2_XS2.3 GB 3.9 GB
Fits Get file →
IQ2_S2.4 GB 4.0 GB
Fits Get file →
IQ2_M2.6 GB 4.2 GB
Fits Get file →
Q2_K_S2.7 GB 4.2 GB
Fits Get file →
Q2_K2.9 GB 4.4 GB
Fits Get file →
IQ3_XXS3.0 GB 4.5 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_K_M3.7 GB 5.2 GB
Fits Get file →
Q3_K_L4.0 GB 5.5 GB
Fits Get file →
IQ4_XS4.1 GB 5.6 GB
Fits Get file →
Q4_04.3 GB 5.9 GB
Fits Get file →
IQ4_NL4.3 GB 5.9 GB
Fits Get file →
Q4_K_S4.3 GB 5.9 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_K_S5.2 GB 6.8 GB
Fits Get file →
Q5_K_M5.3 GB 6.9 GB
Fits Get file →
Q6_K6.1 GB 7.7 GB
Tight Get file →

For 8 GB VRAM, use IQ1_S (1.74 GB, 3.3 GB memory) or IQ1_M (1.88 GB, 3.5 GB memory). For 12 GB VRAM, IQ2_M (2.64 GB, 4.2 GB memory) or Q2_K (2.86 GB, 4.4 GB memory) are suitable. For 16 GB VRAM, Q3_K_L (3.98 GB, 5.5 GB memory) or Q4_K_M (4.54 GB, 6.1 GB memory) provide a balance of size and memory usage.

What GPU do you need for Chihiro-7B-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: the best quant that fits is IQ2_S (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_S (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).

Which Chihiro-7B-v0.1 quant should you choose?

Q4_K_M is the usual starting point for Chihiro-7B-v0.1: it balances file size and quality well. Here it is a 4.5 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

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

Source

Quantized bymradermacher
FamilyChihiro
Licenseunknown
Downloads (HF)1,277
Last updated2025-01-26

Frequently asked questions about Chihiro-7B-v0.1

How much VRAM does Chihiro-7B-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 Chihiro-7B-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 Chihiro-7B-v0.1 GGUF?

It depends on the quant: IQ1_S is 1.7 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.4 GB, IQ2_M is 2.6 GB and 18 more.

What context length does Chihiro-7B-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 Chihiro-7B-v0.1 GGUF?

The files are on Hugging Face in the mradermacher/Chihiro-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 Chihiro-7B-v0.1 use?

Hugging Face lists the license as unknown. 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 Chihiro-7B-v0.1 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantized files; they require approximately 3.3–3.5 GB memory at 8k context.

Does Chihiro-7B-v0.1 support vision?

No, the model does not include vision capabilities.

What prompt format should I use?

Use the prompt templates recommended by Mistral 7B Instruct or Breeze 7B Instruct, or the generic Mistral prompt format.

Other GGUFs of Chihiro-7B-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Chihiro models

All Chihiro →

Other small models

All small models →