ME

mihaiii_metis-0.3

MetisGGUF by TheBlokeUpdated 2023-12-18
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

mihaiii_metis-0.3 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.1 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Metis 0.3 – 7.24B instruct model in GGUF format

Mihai’s Metis 0.3 is an instruct fine‑tune of mistralai/Mistral‑7B‑Instruct‑v0.2. It handles long system prompts and focuses on reasoning and text comprehension. The model is available in multiple GGUF quantisations.

Good at

  • Long‑context reasoning
  • Text comprehension
  • Instruct‑style dialogue

Limits

  • No vision support
  • Not suitable for storytelling
  • Requires 8k context for full performance

Best for

  • Chatbot assistants
  • Educational tutoring
  • Code explanation

Who it’s for. Developers and researchers who need a lightweight, reasoning‑oriented LLM for local deployment. The model is released under apache‑2.0 and can be run with llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (est. 5.9 GB) or Q5_K_S (6.6 GB). With 12 GB VRAM Q5_K_M (6.7 GB) or Q6_K (7.5 GB) are suitable. Larger VRAM allows Q8_0 (9.3 GB).

What GPU do you need for mihaiii_metis-0.3?

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_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which mihaiii_metis-0.3 quant should you choose?

Q4_K_M is the usual starting point for mihaiii_metis-0.3: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 3.1 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTheBloke
FamilyMetis
Licenseapache-2.0
Downloads (HF)1,609
Last updated2023-12-18

Frequently asked questions about mihaiii_metis-0.3

How much VRAM does mihaiii_metis-0.3 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 mihaiii_metis-0.3 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mihaiii_metis-0.3 GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 6 more.

What context length does mihaiii_metis-0.3 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 mihaiii_metis-0.3 GGUF?

The files are on Hugging Face in the TheBloke/Metis-0.3-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 mihaiii_metis-0.3 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 Metis 0.3 on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_S quantisations, which require about 5.9 GB or 6.6 GB of VRAM at 8k context.

Does Metis 0.3 support vision tasks?

No, the model has no vision capabilities and is focused on text.

What license applies to Metis 0.3?

The model is released under the apache‑2.0 license.

Other GGUFs of Metis-0.3

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Metis models

All Metis →

Other small models

All small models →