SH

shizhi twilight 7B i1

ShizhiGGUF by mradermacherUpdated 2024-11-02
Download on Hugging Face
Parameters13.1B
Context32K
Layers32
Architecturellama
Smallest quant2.9 GB
Quick answer

shizhi twilight 7B i1 needs about 9.5 GB of memory at Q4_K_M (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.9 GB (IQ1_S) to 10.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

13.1B Shizhi model with tool‑use capability

shizhi twilight 7B i1 is a 13.1B parameter Llama‑style model. It supports tool usage and is trained on a 32768 token context. The model is released under Apache‑2.0.

Good at

  • Tool‑based instruction following
  • Large context handling
  • Multilingual support

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No explicit language list

Best for

  • Chatbots needing tool integration
  • Long‑form content generation
  • Research prototyping

Who it’s for. Developers and researchers who need a large Llama‑style model with tool support and a generous context window. The model is suitable for experimentation and deployment in environments that can handle its memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 4.4 GB
Fits Get file →
IQ1_M3.1 GB 4.7 GB
Fits Get file →
IQ2_XXS3.6 GB 5.2 GB
Fits Get file →
IQ2_XS4.0 GB 5.5 GB
Fits Get file →
IQ2_S4.1 GB 5.7 GB
Fits Get file →
IQ2_M4.5 GB 6.0 GB
Fits Get file →
Q2_K4.9 GB 6.5 GB
Fits Get file →
IQ3_XXS5.1 GB 6.7 GB
Fits Get file →
IQ3_XS5.5 GB 7.0 GB
Fits Get file →
Q3_K_S5.7 GB 7.3 GB
Tight Get file →
IQ3_S5.8 GB 7.3 GB
Tight Get file →
IQ3_M5.9 GB 7.5 GB
Tight Get file →
Q3_K_M6.4 GB 7.9 GB
Tight Get file →
Q3_K_L6.9 GB 8.5 GB
Too big Get file →
IQ4_XS7.1 GB 8.6 GB
Too big Get file →
Q4_07.5 GB 9.0 GB
Too big Get file →
Q4_07.5 GB 9.0 GB
Too big Get file →
Q4_07.5 GB 9.0 GB
Too big Get file →
Q4_07.5 GB 9.1 GB
Too big Get file →
Q4_K_S7.5 GB 9.1 GB
Too big Get file →
Q4_K_M8.0 GB 9.5 GB
Too big Get file →
Q5_K_S9.1 GB 10.6 GB
Too big Get file →
Q5_K_M9.3 GB 10.9 GB
Too big Get file →
Q6_K10.8 GB 12.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.87 GB, memory 4.4 GB) or IQ1_M (3.14 GB, 4.7 GB). With 12 GB VRAM, Q2_K (4.9 GB, 6.5 GB) or IQ3_M (5.89 GB, 7.5 GB) are suitable. For 24 GB VRAM, Q5_K_M (9.32 GB, 10.9 GB) or Q6_K (10.77 GB, 12.3 GB) provide higher quality.

What GPU do you need for shizhi twilight 7B i1?

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 IQ2_M (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.4 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.3 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.8 GB file, about 12.3 GB in use).

Which shizhi twilight 7B i1 quant should you choose?

Q4_K_M is the usual starting point for shizhi twilight 7B i1: it balances file size and quality well. Here it is a 8.0 GB file.

If memory is tight, the smallest file is IQ1_S 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
Parameters13.1B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyShizhi
Licenseapache-2.0
Downloads (HF)957
Last updated2024-11-02

Frequently asked questions about shizhi twilight 7B i1

How much VRAM does shizhi twilight 7B i1 need?

About 9.5 GB at Q4_K_M with an 8K context window. That is the 8.0 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 shizhi twilight 7B i1 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of shizhi twilight 7B i1 GGUF?

It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 4.0 GB, IQ2_S is 4.1 GB, IQ2_M is 4.5 GB and 18 more.

What context length does shizhi twilight 7B i1 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 shizhi twilight 7B i1 GGUF?

The files are on Hugging Face in the mradermacher/shizhi-twilight-7B-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 shizhi twilight 7B i1 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 shizhi twilight 7B i1 on 8 GB VRAM?

Yes, with IQ1_S or IQ1_M quantizations the estimated VRAM usage is below 8 GB.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of shizhi-twilight-7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Shizhi models

All Shizhi →

Other medium models

All medium models →