RO

RoMistral-7b-Instruct

RomistralGGUF by legraphistaUpdated 2024-05-25
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

RoMistral-7b-Instruct needs about 4.9 GB of memory at IQ3_M (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 1.6 GB (IQ1_S) to 14.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

RoMistral‑7b‑Instruct: Romanian instruction‑tuned LLM

RoMistral‑7b‑Instruct is a 7‑billion‑parameter Llama‑based model fine‑tuned for Romanian instruction following. It supports up to 32,768‑token context and is released under a CC‑BY‑NC‑4.0 license.

Good at

  • Instruction following in Romanian
  • Chat‑style interactions
  • Text generation with 32k context

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • CC‑BY‑NC‑4.0 license limits commercial use

Best for

  • Building Romanian chat assistants
  • Research on Romanian NLP
  • Fine‑tuning for domain‑specific tasks

Who it’s for. Researchers and developers needing a Romanian‑focused instruction model. The model is suitable for academic projects and non‑commercial applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.8 GB 3.3 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K_S2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
IQ4_NL4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K5.1 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 →
BF1614.5 GB 16.1 GB
Too big Get file →
—14.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.61 GB) or IQ1_M (1.75 GB). With 12 GB VRAM, Q2_K (2.72 GB) or Q3_K (3.52 GB) provide a good balance of size and performance. For 24 GB VRAM, Q5_K (5.13 GB) or Q6_K (5.94 GB) are recommended.

What GPU do you need for RoMistral-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: the best quant that fits is IQ2_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K (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).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (14.5 GB file, about 16.1 GB in use).

Which RoMistral-7b-Instruct quant should you choose?

IQ3_M (3.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 1.6 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 bylegraphista
FamilyRomistral
Downloads (HF)7,072
Last updated2024-05-25

Frequently asked questions about RoMistral-7b-Instruct

How much VRAM does RoMistral-7b-Instruct need?

About 4.9 GB at IQ3_M with an 8K context window. That is the 3.3 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 RoMistral-7b-Instruct 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 RoMistral-7b-Instruct GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 19 more.

What context length does RoMistral-7b-Instruct 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 RoMistral-7b-Instruct GGUF?

The files are on Hugging Face in the legraphista/RoMistral-7b-Instruct-IMat-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 RoMistral-7b-Instruct use?

Hugging Face lists the license as cc-by-nc-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 RoMistral‑7b‑Instruct on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with approximate 3.2–3.3 GB memory usage at 8k context.

Does the model support image inputs?

No, RoMistral‑7b‑Instruct does not include vision capabilities.

Is the model free for commercial use?

No, the CC‑BY‑NC‑4.0 license restricts commercial deployment.

Other GGUFs of RoMistral-7b-Instruct

Similar models

Browse all →

More from legraphista

All by legraphista →

More Romistral models

All Romistral →

Other small models

All small models →