LL

Llama-3-Instruct-8B-SPPO-Iter3

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

Llama-3-Instruct-8B-SPPO-Iter3 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).

Llama‑3‑Instruct‑8B fine‑tuned with Self‑Play Preference Optimization

Llama‑3‑Instruct‑8B‑SPPO‑Iter3 is an 8B parameter GPT‑like model based on Meta‑Llama‑3‑8B‑Instruct. It was trained with Self‑Play Preference Optimization using synthetic datasets from UltraFeedback. The model is licensed under Apache‑2.0.

Good at

  • Fine‑tuned instruction following
  • Synthetic dataset alignment
  • English‑centric responses

Limits

  • No vision support
  • Requires 8192 token context
  • No non‑English language data

Best for

  • Chatbot prototypes
  • Instruction‑driven applications
  • Synthetic data generation

Who it’s for. Developers building instruction‑oriented chatbots or research prototypes that need a lightweight 8B model. The model is suitable for users who prefer an Apache‑2.0 licensed LLM and can work within the 8192 token context limit.

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 Q4_0 (file size 4.68 GB, estimated 6.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (5.73 GB, 7.3 GB memory) or Q6_K (6.6 GB, 8.2 GB memory). For 16 GB VRAM, Q6_K offers the largest quant with acceptable memory usage.

What GPU do you need for Llama-3-Instruct-8B-SPPO-Iter3?

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 Llama-3-Instruct-8B-SPPO-Iter3 quant should you choose?

Q4_K_M is the usual starting point for Llama-3-Instruct-8B-SPPO-Iter3: 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
Licenseapache-2.0
Downloads (HF)1,686
Last updated2024-08-02

Frequently asked questions about Llama-3-Instruct-8B-SPPO-Iter3

How much VRAM does Llama-3-Instruct-8B-SPPO-Iter3 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 Llama-3-Instruct-8B-SPPO-Iter3 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 Llama-3-Instruct-8B-SPPO-Iter3 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 Llama-3-Instruct-8B-SPPO-Iter3 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 Llama-3-Instruct-8B-SPPO-Iter3 GGUF?

The files are on Hugging Face in the mradermacher/Llama-3-Instruct-8B-SPPO-Iter3-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 Llama-3-Instruct-8B-SPPO-Iter3 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 this model on 8 GB VRAM?

Yes, the Q4_0 quant requires about 6.2 GB memory at 8k context, which fits within an 8 GB VRAM budget.

Does this model support vision tasks?

No, the model has no vision capability and is designed for text only.

What license does the model use?

The model is released under the Apache‑2.0 license.

Other GGUFs of Llama-3-Instruct-8B-SPPO-Iter3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →