VI

bofenghuang_vigogne-2-7b-instruct

VigogneGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters6.74B
Context2K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

bofenghuang_vigogne-2-7b-instruct 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 12 quants, from 2.8 GB (Q2_K) to 7.2 GB (Q8_0).

Vigogne‑2‑7B‑Instruct, a French instruction‑following LLaMA‑2‑based model

Vigogne‑2‑7B‑Instruct is a 6.74 billion‑parameter LLaMA‑2‑based model fine‑tuned to follow French instructions. It is released under the llama2 license and supports a 2048‑token context window. The model is available in multiple GGUF quantisations.

Good at

  • French instruction following
  • Short‑form explanations
  • Conversational French dialogue

Limits

  • No vision support
  • Limited to 2048‑token context
  • Requires llama.cpp or compatible GGUF client

Best for

  • French language tutoring
  • Generating French FAQs
  • Chatbot integration in French apps

Who it’s for. Developers building French‑language chatbots or educational tools. Researchers needing a French instruction‑following model for experimentation. Users wanting a lightweight French LLM for local inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 4.4 GB
Fits Get file →
Q3_K_S2.9 GB 4.5 GB
Fits Get file →
Q3_K_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_L3.6 GB 5.2 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_K_S3.9 GB 5.4 GB
Fits Get file →
Q4_K_M4.1 GB 5.7 GB
Fits Get file →
Q5_04.7 GB 6.2 GB
Fits Get file →
Q5_K_S4.7 GB 6.2 GB
Fits Get file →
Q5_K_M4.8 GB 6.4 GB
Fits Get file →
Q6_K5.5 GB 7.1 GB
Fits Get file →
Q8_07.2 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, Q4_K (7.6 GB) or Q4_K_M (8.9 GB) are suitable. For 12 GB VRAM, Q4_0 (8.6 GB) or Q5_0 (9.4 GB) fit well. For 16 GB VRAM, Q6_K (10.3 GB) or Q8_0 (12 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for bofenghuang_vigogne-2-7b-instruct?

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 Q3_K_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which bofenghuang_vigogne-2-7b-instruct quant should you choose?

Q4_K_M is the usual starting point for bofenghuang_vigogne-2-7b-instruct: 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 Q2_K at 2.8 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 context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
FamilyVigogne
Licensellama2
Downloads (HF)2,967
Last updated2023-09-27

Frequently asked questions about bofenghuang_vigogne-2-7b-instruct

How much VRAM does bofenghuang_vigogne-2-7b-instruct 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 bofenghuang_vigogne-2-7b-instruct on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 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 bofenghuang_vigogne-2-7b-instruct GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does bofenghuang_vigogne-2-7b-instruct support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download bofenghuang_vigogne-2-7b-instruct GGUF?

The files are on Hugging Face in the TheBloke/Vigogne-2-7B-Instruct-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 bofenghuang_vigogne-2-7b-instruct 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 Vigogne‑2‑7B‑Instruct on 8 GB VRAM?

Yes, using Q4_K or Q4_K_M quantisations, which require about 7.6–8.9 GB of VRAM at 8k context.

Does this model support image inputs?

No, Vigogne‑2‑7B‑Instruct has no vision capability.

What license applies to this model?

The model is released under the llama2 license, following LLaMA‑2 usage policy.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Vigogne models

All Vigogne →

Other small models

All small models →