LL

Emma 500 Llama2 7b

LlamaGGUF by bartowskiUpdated 2024-09-30
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.4 GB
Quick answer

Emma 500 Llama2 7b needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.4 GB (IQ2_M) to 13.5 GB (F16).

Emma 500 Llama2 7b – a 7B multilingual Llama 2 model

Emma 500 Llama2 7b is a 6.74B parameter Llama 2 model fine‑tuned on the MaLA Corpus. It supports 546 languages and excels in multilingual tasks such as translation, commonsense reasoning, and open‑ended generation. The model is available in multiple GGUF quantizations.

Good at

  • Multilingual translation
  • Commonsense reasoning
  • Open‑ended generation

Limits

  • No vision support
  • Requires 8k context
  • License is llama2

Best for

  • Multilingual chatbots
  • Code generation in multiple languages
  • Text classification across 546 languages

Who it’s for. Developers building multilingual applications who need a compact Llama 2 base. Researchers focusing on low‑resource language performance can also benefit from the extensive MaLA training data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M2.4 GB 5.0 GB
Fits Get file →
Q2_K2.5 GB 5.2 GB
Fits Get file →
Q2_K_L2.7 GB 5.3 GB
Fits Get file →
IQ3_XS2.8 GB 5.4 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
IQ3_M3.1 GB 5.8 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
IQ4_XS3.6 GB 6.3 GB
Fits Get file →
Q3_K_XL3.7 GB 6.4 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q4_K_L4.2 GB 6.8 GB
Fits Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q5_K_L4.9 GB 7.5 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q6_K_L5.6 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →
F1613.5 GB 16.1 GB
Too big Get file →

For 8GB VRAM use Q4_K_M (file size 4.08GB, ~8.9GB memory). With 12GB VRAM Q6_K (5.53GB, ~10.3GB memory) or Q6_K_L (5.59GB, ~10.4GB). For 16GB VRAM Q8_0 (7.16GB, ~12GB memory) is suitable. File sizes and memory estimates are approximate.

What GPU do you need for Emma 500 Llama2 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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which Emma 500 Llama2 7b quant should you choose?

Q4_K_M is the usual starting point for Emma 500 Llama2 7b: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_M 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bybartowski
FamilyLlama
Licensellama2
Downloads (HF)3,090
Last updated2024-09-30

Frequently asked questions about Emma 500 Llama2 7b

How much VRAM does Emma 500 Llama2 7b need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Emma 500 Llama2 7b on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 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 Emma 500 Llama2 7b GGUF?

It depends on the quant: IQ2_M is 2.4 GB, Q2_K is 2.5 GB, Q2_K_L is 2.7 GB, IQ3_XS is 2.8 GB, Q3_K_S is 2.9 GB, IQ3_M is 3.1 GB and 18 more.

What context length does Emma 500 Llama2 7b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Emma 500 Llama2 7b GGUF?

The files are on Hugging Face in the bartowski/emma-500-llama2-7b-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 Emma 500 Llama2 7b use?

Hugging Face lists the license as llama2. 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 Emma 500 Llama2 7b on 8GB VRAM?

Yes, use a quant like Q4_K_M which requires about 8.9GB of memory at 8k context.

Does the model support vision tasks?

No, Emma 500 Llama2 7b does not include vision capabilities.

What license applies to this model?

The model is licensed under the llama2 license.

Other GGUFs of emma-500-llama2-7b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Llama models

All Llama →

Other small models

All small models →