CL

Claire 7B 0.1

ClaireGGUF by mradermacherUpdated 2024-09-03
Download on Hugging Face
Parameters7.22B
Context2K
Layers32
Architecturefalcon
Smallest quant3.3 GB
Quick answer

Claire 7B 0.1 needs about 5.5 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 21 quants, from 3.3 GB (IQ1_S) to 7.0 GB (Q6_K).

Claire 7B 0.1 – a 7B parameter Falcon‑based dialogue model

Claire 7B 0.1 is a 7.22B parameter causal decoder‑only model built by LINAGORA and OpenLLM‑France. It is adapted from Falcon‑7b on French conversational data and is designed to generate dialogue continuations. The model is available in multiple GGUF quantizations.

Good at

  • Dialogue generation in French
  • Dialogue understanding tasks
  • Fine‑tuning base for chat models

Limits

  • Requires at least 6GB VRAM for 4‑bit inference
  • No vision support
  • CC‑BY‑NC‑SA‑4.0 license

Best for

  • Chatbot prototypes
  • Meeting summarization
  • Dialogue data augmentation

Who it’s for. Developers building French language chat applications or researchers fine‑tuning dialogue models. The model is suitable for those who need a lightweight base for further training.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.3 GB 3.8 GB
Fits Get file →
IQ1_M3.3 GB 3.9 GB
Fits Get file →
IQ2_XXS3.4 GB 3.9 GB
Fits Get file →
IQ2_XS3.5 GB 4.0 GB
Fits Get file →
IQ2_S3.5 GB 4.1 GB
Fits Get file →
IQ2_M3.6 GB 4.1 GB
Fits Get file →
IQ3_XXS3.7 GB 4.3 GB
Fits Get file →
IQ3_S3.9 GB 4.4 GB
Fits Get file →
IQ3_XS3.9 GB 4.4 GB
Fits Get file →
Q2_K3.9 GB 4.4 GB
Fits Get file →
Q3_K_S3.9 GB 4.4 GB
Fits Get file →
IQ3_M4.0 GB 4.5 GB
Fits Get file →
IQ4_XS4.1 GB 4.6 GB
Fits Get file →
Q3_K_M4.1 GB 4.7 GB
Fits Get file →
Q4_04.2 GB 4.7 GB
Fits Get file →
Q3_K_L4.4 GB 4.9 GB
Fits Get file →
Q4_K_S4.7 GB 5.3 GB
Fits Get file →
Q4_K_M5.0 GB 5.5 GB
Fits Get file →
Q5_K_S5.3 GB 5.9 GB
Fits Get file →
Q5_K_M5.7 GB 6.2 GB
Fits Get file →
Q6_K7.0 GB 7.5 GB
Tight Get file →

For 8GB VRAM, use IQ1_S (3.28 GB) or IQ1_M (3.34 GB). For 12GB VRAM, IQ2_S (3.53 GB) or Q2_K (3.86 GB) provide a good balance of size and performance. For 16GB VRAM, Q4_K_M (4.98 GB) or Q5_K_M (5.73 GB) offer higher quality while staying within memory limits. Estimates are approximate.

What GPU do you need for Claire 7B 0.1?

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 (3.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_S (5.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 7.6 GB in use).

Which Claire 7B 0.1 quant should you choose?

Q4_K_M is the usual starting point for Claire 7B 0.1: it balances file size and quality well. Here it is a 5.0 GB file.

If memory is tight, the smallest file is IQ1_S at 3.3 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

Architecturefalcon
Parameters7.22B
Layers32
Trained context2,048 tokens
KV cache (fp16)8 KB per token

Source

Quantized bymradermacher
FamilyClaire
Downloads (HF)2,058
Last updated2024-09-03

Frequently asked questions about Claire 7B 0.1

How much VRAM does Claire 7B 0.1 need?

About 5.5 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Claire 7B 0.1 on an 8 GB GPU?

Yes, with Q6_K: the 7.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Claire 7B 0.1 GGUF?

It depends on the quant: IQ1_S is 3.3 GB, IQ1_M is 3.3 GB, IQ2_XXS is 3.4 GB, IQ2_XS is 3.5 GB, IQ2_S is 3.5 GB, IQ2_M is 3.6 GB and 15 more.

What context length does Claire 7B 0.1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download Claire 7B 0.1 GGUF?

The files are on Hugging Face in the mradermacher/Claire-7B-0.1-i1-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 Claire 7B 0.1 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Claire 7B 0.1 on 8 GB VRAM?

Yes, using a 4‑bit quant like IQ1_S or IQ1_M will fit within 8 GB VRAM. The estimated memory usage is about 3.9 GB at 8k context.

Does the model support English?

The model was trained on French conversational data and is primarily tuned for French dialogue. It may handle English but performance is not guaranteed.

What license applies to the model?

The model is released under cc‑by‑nc‑sa‑4.0, which allows non‑commercial use with attribution and share‑alike.

Other GGUFs of Claire-7B-0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Claire models

All Claire →

Other small models

All small models →