LL

yo-Llama-3-8B-Instruct

LlamaGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

yo-Llama-3-8B-Instruct needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K).

Yo‑Llama‑3‑8B‑Instruct: Llama‑3‑8B steered to rap style

Yo‑Llama‑3‑8B‑Instruct is a 8‑billion‑parameter Llama model that has been steered to respond in a rap style. It is based on Llama‑3‑8B‑Instruct weights and uses a feature‑direction approach rather than traditional fine‑tuning. The model supports a 8192‑token context window.

Good at

  • Rap‑style responses
  • Instruction following
  • Creative text generation

Limits

  • No vision support
  • Not fine‑tuned for general tasks
  • License: llama3

Best for

  • Generating rap lyrics
  • Creative writing prompts
  • Instructional dialogue in rap format

Who it’s for. Developers and researchers interested in style‑steering experiments. The model is suitable for those who want to explore activation‑space manipulation rather than conventional fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XS (2.61 GB, 4.2 GB memory) or Q4_0 (4.68 GB, 6.2 GB memory). For 12‑GB VRAM, IQ3_XS (3.52 GB, 5.1 GB memory) or Q4_K_M (4.92 GB, 6.5 GB memory) are good choices. Higher‑quality quants like Q5_K_M (5.73 GB, 7.3 GB memory) require 16‑GB VRAM or more.

What GPU do you need for yo-Llama-3-8B-Instruct?

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_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which yo-Llama-3-8B-Instruct quant should you choose?

Q4_K_M is the usual starting point for yo-Llama-3-8B-Instruct: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 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
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3
Downloads (HF)1,546
Last updated2024-08-02

Frequently asked questions about yo-Llama-3-8B-Instruct

How much VRAM does yo-Llama-3-8B-Instruct need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 yo-Llama-3-8B-Instruct on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of yo-Llama-3-8B-Instruct GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 15 more.

What context length does yo-Llama-3-8B-Instruct support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download yo-Llama-3-8B-Instruct GGUF?

The files are on Hugging Face in the mradermacher/yo-Llama-3-8B-Instruct-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 yo-Llama-3-8B-Instruct use?

Hugging Face lists the license as llama3. 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 Yo‑Llama‑3‑8B‑Instruct on 8 GB VRAM?

Yes, use IQ2_XS or Q4_0 quant files, which fit within 8 GB VRAM with approximate memory usage of 4.2 GB or 6.2 GB respectively.

Does this model support image input?

No, the model has no vision capability.

What license applies to this model?

The model is released under the llama3 license.

Other GGUFs of yo-Llama-3-8B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →