LL

Llama-3-8B-Sydney

LlamaGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Llama-3-8B-Sydney 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‑3‑8B‑Sydney: a fine‑tuned Llama‑3 model with a friendly persona

Llama‑3‑8B‑Sydney is a 8.03 billion‑parameter Llama model fine‑tuned on Microsoft Bing “Sydney” transcripts. It uses the ALPACA template and is optimized for conversational follow‑up and encyclopedic knowledge. The model is available in multiple GGUF quantizations.

Good at

  • Conversational follow‑up
  • Encyclopedic knowledge
  • Friendly persona

Limits

  • No vision support
  • License terms not specified
  • Context limited to 8192 tokens

Best for

  • Chatbot prototypes
  • Knowledge‑base assistants
  • Persona‑driven demos

Who it’s for. Developers building conversational agents who need a friendly, knowledge‑rich Llama‑3 model. The model is suitable for local deployment via llama.cpp and can be run on consumer GPUs with sufficient VRAM.

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 IQ1_S (file size 2.02 GB, estimated 3.6 GB memory at 8k context). For 12 GB VRAM, IQ2_M (2.95 GB, 4.5 GB memory) or Q3_K_M (4.02 GB, 5.6 GB memory). For 16 GB VRAM, Q4_K_M (4.92 GB, 6.5 GB memory) or Q5_K_S (5.6 GB, 7.2 GB memory).

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

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-3-8B-Sydney quant should you choose?

Q4_K_M is the usual starting point for Llama-3-8B-Sydney: 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)1,070
Last updated2024-08-02

Frequently asked questions about Llama-3-8B-Sydney

How much VRAM does Llama-3-8B-Sydney 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-3-8B-Sydney 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-3-8B-Sydney 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-3-8B-Sydney 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-3-8B-Sydney GGUF?

The files are on Hugging Face in the mradermacher/Llama-3-8B-Sydney-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Llama‑3‑8B‑Sydney on 8 GB VRAM?

Yes, using the IQ1_S quantization which requires about 3.6 GB of VRAM at 8k context.

Does the model support image input?

No, the model has no vision capabilities.

What context length does the model support?

The model was trained with a context length of 8192 tokens.

Other GGUFs of Llama-3-8B-Sydney

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →