ME

Meltemi 7B Instruct v1.5

MeltemiGGUF by mradermacherUpdated 2024-08-06
Download on Hugging Face
Parameters7.48B
Context32K
Layers32
Architecturellama
Smallest quant2.9 GB
Quick answer

Meltemi 7B Instruct v1.5 needs about 6.1 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 2.9 GB (Q2_K) to 15.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Meltemi 7B Instruct v1.5 – Greek‑focused instruction LLM

Meltemi 7B Instruct v1.5 is a 7.48B parameter LLM fine‑tuned for Greek instruction following. It uses a 32768 token context window and is trained with ORPO on 97k preference examples. The model is released under the Apache‑2.0 license.

Good at

  • Greek instruction following
  • Greek language understanding
  • Few‑shot reasoning in Greek

Limits

  • No vision support
  • Requires 32768 token context
  • License is Apache‑2.0

Best for

  • Greek chatbots
  • Greek content generation
  • Greek QA systems

Who it’s for. Developers building Greek‑centric applications who need a lightweight instruction model. The model is suitable for local deployment with llama.cpp and supports a variety of quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.9 GB 4.4 GB
Fits Get file →
IQ3_XS3.2 GB 4.7 GB
Fits Get file →
Q3_K_S3.3 GB 4.9 GB
Fits Get file →
IQ3_S3.3 GB 4.9 GB
Fits Get file →
IQ3_M3.4 GB 5.0 GB
Fits Get file →
Q3_K_M3.7 GB 5.2 GB
Fits Get file →
Q3_K_L4.0 GB 5.5 GB
Fits Get file →
IQ4_XS4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.3 GB 5.9 GB
Fits Get file →
Q4_K_M4.5 GB 6.1 GB
Fits Get file →
Q5_K_S5.2 GB 6.8 GB
Fits Get file →
Q5_K_M5.3 GB 6.9 GB
Fits Get file →
Q6_K6.1 GB 7.7 GB
Tight Get file →
Q8_08.0 GB 9.5 GB
Too big Get file →
F1615.0 GB 16.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 4.54 GB, estimated 6.1 GB memory). For 12 GB VRAM use Q5_K_M (5.31 GB, 6.9 GB memory). For 16 GB VRAM use Q6_K (6.14 GB, 7.7 GB memory).

What GPU do you need for Meltemi 7B Instruct v1.5?

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: the best quant that fits is Q4_K_S (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.0 GB file, about 16.5 GB in use).

Which Meltemi 7B Instruct v1.5 quant should you choose?

Q4_K_M is the usual starting point for Meltemi 7B Instruct v1.5: it balances file size and quality well. Here it is a 4.5 GB file.

The Q8_0 file is 8.0 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 Q2_K at 2.9 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
Parameters7.48B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMeltemi
Licenseapache-2.0
Downloads (HF)996
Last updated2024-08-06

Frequently asked questions about Meltemi 7B Instruct v1.5

How much VRAM does Meltemi 7B Instruct v1.5 need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 4.5 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 Meltemi 7B Instruct v1.5 on an 8 GB GPU?

Yes, with Q6_K: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Meltemi 7B Instruct v1.5 GGUF?

It depends on the quant: Q2_K is 2.9 GB, IQ3_XS is 3.2 GB, Q3_K_S is 3.3 GB, IQ3_S is 3.3 GB, IQ3_M is 3.4 GB, Q3_K_M is 3.7 GB and 9 more.

What context length does Meltemi 7B Instruct v1.5 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Meltemi 7B Instruct v1.5 GGUF?

The files are on Hugging Face in the mradermacher/Meltemi-7B-Instruct-v1.5-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 Meltemi 7B Instruct v1.5 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 Meltemi 7B Instruct v1.5 on 8 GB VRAM?

Yes, using Q4_K_M which requires approximately 6.1 GB memory at 8 k context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Meltemi-7B-Instruct-v1.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Meltemi models

All Meltemi →

Other small models

All small models →