IN

Yi Ko 6B

InstructGGUF by mradermacherUpdated 2024-11-05
Download on Hugging Face
Parameters6.18B
Context2K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

Yi Ko 6B needs about 4.8 GB of memory at Q4_K_M (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 21 quants, from 1.5 GB (IQ1_S) to 5.1 GB (Q6_K).

Yi Ko 6B Instruct model, 6.18B parameters, 2048 token context

Yi Ko 6B is an instruct‑style model based on the llama architecture. It contains 6.18B parameters and supports a 2048 token context window. The model is released under a cc‑by‑nc‑4.0 license.

Good at

  • Instruction following
  • Short‑form Q&A
  • Language‑specific tasks

Limits

  • No vision support
  • Limited to 2048 token context
  • cc‑by‑nc‑4.0 license restricts commercial use

Best for

  • Chatbots with moderate context
  • Educational tutoring
  • Content summarization

Who it’s for. Developers building instruction‑driven applications who need a compact model with a 2048 token window. The model is suitable for non‑commercial projects due to its license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 2.1 GB
Fits Get file →
IQ1_M1.6 GB 2.2 GB
Fits Get file →
IQ2_XXS1.8 GB 2.4 GB
Fits Get file →
IQ2_XS2.0 GB 2.6 GB
Fits Get file →
IQ2_S2.1 GB 2.7 GB
Fits Get file →
IQ2_M2.2 GB 2.9 GB
Fits Get file →
Q2_K2.4 GB 3.0 GB
Fits Get file →
IQ3_XXS2.5 GB 3.1 GB
Fits Get file →
IQ3_XS2.7 GB 3.3 GB
Fits Get file →
Q3_K_S2.8 GB 3.4 GB
Fits Get file →
IQ3_S2.8 GB 3.4 GB
Fits Get file →
IQ3_M2.9 GB 3.5 GB
Fits Get file →
Q3_K_M3.1 GB 3.7 GB
Fits Get file →
Q3_K_L3.3 GB 3.9 GB
Fits Get file →
IQ4_XS3.4 GB 4.0 GB
Fits Get file →
Q4_03.6 GB 4.2 GB
Fits Get file →
Q4_K_S3.6 GB 4.2 GB
Fits Get file →
Q4_K_M3.8 GB 4.4 GB
Fits Get file →
Q5_K_S4.3 GB 4.9 GB
Fits Get file →
Q5_K_M4.4 GB 5.0 GB
Fits Get file →
Q6_K5.1 GB 5.7 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (1.49 GB, 2.5 GB memory) or IQ1_M (1.6 GB, 2.6 GB memory). If 12 GB VRAM is available, Q4_K_M (3.76 GB, 4.8 GB memory) offers a good balance of size and performance. Larger quants such as Q5_K_M or Q6_K require more than 16 GB VRAM.

What GPU do you need for Yi Ko 6B?

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 IQ3_M (2.9 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (4.4 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.1 GB file, about 6.1 GB in use).

Which Yi Ko 6B quant should you choose?

Q4_K_M is the usual starting point for Yi Ko 6B: it balances file size and quality well. Here it is a 3.8 GB file.

If memory is tight, the smallest file is IQ1_S at 1.5 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
Parameters6.18B
Layers32
Trained context2,048 tokens
KV cache (fp16)64 KB per token

Source

Quantized bymradermacher
FamilyInstruct
Downloads (HF)488
Last updated2024-11-05

Frequently asked questions about Yi Ko 6B

How much VRAM does Yi Ko 6B need?

About 4.8 GB at Q4_K_M with an 8K context window. That is the 3.8 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 Yi Ko 6B on an 8 GB GPU?

Yes, with Q6_K: the 5.1 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Yi Ko 6B GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.6 GB, IQ2_XXS is 1.8 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.1 GB, IQ2_M is 2.2 GB and 15 more.

What context length does Yi Ko 6B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.1 GB at 2K.

Where can I download Yi Ko 6B GGUF?

The files are on Hugging Face in the mradermacher/Yi-Ko-6B-Instruct-v1.1-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 Yi Ko 6B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Yi Ko 6B on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant files; they require about 2.5–2.6 GB VRAM at 8k context.

Does Yi Ko 6B support vision tasks?

No, the model is purely text‑based and has no vision capability.

Is Yi Ko 6B suitable for commercial use?

The cc‑by‑nc‑4.0 license prohibits commercial use without permission.

Other GGUFs of Yi-Ko-6B-Instruct-v1.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Instruct models

All Instruct →

Other small models

All small models →