GE

Genstruct 10.7B

GenstructGGUF by mradermacherUpdated 2024-12-08
Download on Hugging Face
Parameters10.7B
Context32K
Layers48
Architecturellama
Smallest quant2.4 GB
Quick answer

Genstruct 10.7B needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 2.4 GB (IQ1_S) to 8.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Genstruct 10.7B is a 10.7B-parameter Genstruct model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 25 quant files, from 2.4 GB (IQ1_S) to 8.8 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 4.5 GB
Fits Get file →
IQ1_M2.6 GB 4.7 GB
Fits Get file →
IQ2_XXS2.9 GB 5.0 GB
Fits Get file →
IQ2_XS3.2 GB 5.3 GB
Fits Get file →
IQ2_S3.4 GB 5.5 GB
Fits Get file →
IQ2_M3.7 GB 5.8 GB
Fits Get file →
Q2_K_S3.7 GB 5.8 GB
Fits Get file →
Q2_K4.0 GB 6.1 GB
Fits Get file →
IQ3_XXS4.2 GB 6.3 GB
Fits Get file →
IQ3_XS4.4 GB 6.6 GB
Fits Get file →
Q3_K_S4.7 GB 6.8 GB
Fits Get file →
IQ3_S4.7 GB 6.8 GB
Fits Get file →
IQ3_M4.8 GB 7.0 GB
Fits Get file →
Q3_K_M5.2 GB 7.3 GB
Tight Get file →
Q3_K_L5.7 GB 7.8 GB
Tight Get file →
IQ4_XS5.8 GB 7.9 GB
Tight Get file →
Q4_06.1 GB 8.2 GB
Too big Get file →
Q4_06.1 GB 8.2 GB
Too big Get file →
Q4_06.1 GB 8.2 GB
Too big Get file →
Q4_06.1 GB 8.2 GB
Too big Get file →
Q4_K_S6.1 GB 8.2 GB
Too big Get file →
Q4_K_M6.5 GB 8.6 GB
Too big Get file →
Q5_K_S7.4 GB 9.5 GB
Too big Get file →
Q5_K_M7.6 GB 9.7 GB
Too big Get file →
Q6_K8.8 GB 10.9 GB
Too big Get file →

What GPU do you need for Genstruct 10.7B?

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 Q2_K_S (3.7 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).

Which Genstruct 10.7B quant should you choose?

Q4_K_M is the usual starting point for Genstruct 10.7B: it balances file size and quality well. Here it is a 6.5 GB file.

If memory is tight, the smallest file is IQ1_S at 2.4 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
Parameters10.7B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyGenstruct
Licenseapache-2.0
Downloads (HF)490
Last updated2024-12-08

Frequently asked questions about Genstruct 10.7B

How much VRAM does Genstruct 10.7B need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 Genstruct 10.7B on an 8 GB GPU?

Yes, with IQ4_XS: the 5.8 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 Genstruct 10.7B GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.2 GB, IQ2_S is 3.4 GB, IQ2_M is 3.7 GB and 19 more.

What context length does Genstruct 10.7B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Genstruct 10.7B GGUF?

The files are on Hugging Face in the mradermacher/Genstruct-10.7B-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 Genstruct 10.7B 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.

Other GGUFs of Genstruct-10.7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Genstruct models

All Genstruct →

Other medium models

All medium models →