RO

RoLlama2 7b Base

RollamaGGUF by mradermacherUpdated 2024-10-11
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

RoLlama2 7b Base 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 14 quants, from 2.5 GB (Q2_K) to 7.2 GB (Q8_0).

RoLlama2 7b Base – Romanian LLM, 6.74B parameters

RoLlama2 7b Base is a Romanian‑focused generative text model built on Llama‑2‑7b. It is released under the Llama2 Community License and trained on CulturaX data. The model supports a 4096 token context window.

Good at

  • Romanian language generation
  • Research‑grade text tasks
  • Fine‑tuning for downstream NLP

Limits

  • No vision support
  • License restricts non‑research use
  • Context limited to 4096 tokens

Best for

  • Academic research in Romanian
  • Fine‑tuning for Romanian NLP tasks
  • Prototype Romanian chat assistants

Who it’s for. Researchers and developers working with Romanian language models. The base model can be adapted for a range of natural language tasks, while instruction and chat variants are intended for assistant‑like chat.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 5.2 GB
Fits Get file →
IQ3_XS2.8 GB 5.4 GB
Fits Get file →
IQ3_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
IQ3_M3.1 GB 5.8 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
IQ4_XS3.6 GB 6.3 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 3.86 GB, estimated memory 8.7 GB). For 12 GB VRAM, Q8_0 (file size 7.16 GB, estimated memory 12 GB) provides full precision. Smaller quants like Q2_K or IQ3_XS reduce VRAM needs but increase memory usage slightly.

What GPU do you need for RoLlama2 7b Base?

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 IQ3_M (3.1 GB file, about 7.9 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 RoLlama2 7b Base quant should you choose?

Q4_K_M is the usual starting point for RoLlama2 7b Base: 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 2.5 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 context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyRollama
Licensellama2
Downloads (HF)1,077
Last updated2024-10-11

Frequently asked questions about RoLlama2 7b Base

How much VRAM does RoLlama2 7b Base 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 RoLlama2 7b Base on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RoLlama2 7b Base GGUF?

It depends on the quant: Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB, IQ3_M is 3.1 GB, Q3_K_M is 3.3 GB and 8 more.

What context length does RoLlama2 7b Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download RoLlama2 7b Base GGUF?

The files are on Hugging Face in the mradermacher/RoLlama2-7b-Base-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 RoLlama2 7b Base 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 RoLlama2 7b Base on 8 GB VRAM?

Yes, the Q4_K_S quant uses about 8.7 GB of VRAM at 8k context, which fits within an 8 GB GPU with some headroom.

Does the model support English?

The model is specialized for Romanian; use in other languages is out of scope.

What license does it use?

The model is released under the Llama2 Community License Agreement.

Other GGUFs of RoLlama2-7b-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rollama models

All Rollama →

Other small models

All small models →