BA

BanglaLLama-3-8b-BnWiki-Base

BanglallamaGGUF by mradermacherUpdated 2025-03-29
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

BanglaLLama-3-8b-BnWiki-Base needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 3.2 GB (Q2_K) to 16.1 GB (F16).

Bangla LLaMA‑3 8B base model for Bangla and English causal language modeling

BanglaLLama‑3‑8b‑BnWiki‑Base is an 8.03 billion‑parameter Llama model pre‑trained on Bangla Wikipedia. It supports causal language modeling in Bangla and English. The model is released under the GNU GPL v3.0 and is ready for inference or further fine‑tuning.

Good at

  • Bangla language generation
  • English language support
  • Causal LM tasks

Limits

  • No instruction following
  • Not detoxified
  • No vision support

Best for

  • Bangla text completion
  • Bangla NLP research
  • Fine‑tuning for Bangla applications

Who it’s for. Researchers and developers needing a Bangla‑centric LLM for causal language modeling. The model can be fine‑tuned for specific NLP tasks but should be used with supervision due to lack of detoxification.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.5 GB 6.1 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.92 GB, estimated 6.5 GB memory). For 12 GB VRAM, Q5_K_M (5.73 GB, 7.3 GB memory) or Q6_K (6.6 GB, 8.2 GB memory). Higher‑precision quants require more memory and are not recommended for limited VRAM.

What GPU do you need for BanglaLLama-3-8b-BnWiki-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: the best quant that fits is Q3_K_L (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which BanglaLLama-3-8b-BnWiki-Base quant should you choose?

Q4_K_M is the usual starting point for BanglaLLama-3-8b-BnWiki-Base: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 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 3.2 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licensellama3
Downloads (HF)687
Last updated2025-03-29

Frequently asked questions about BanglaLLama-3-8b-BnWiki-Base

How much VRAM does BanglaLLama-3-8b-BnWiki-Base need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 BanglaLLama-3-8b-BnWiki-Base on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of BanglaLLama-3-8b-BnWiki-Base GGUF?

It depends on the quant: Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB, Q3_K_M is 4.0 GB and 9 more.

What context length does BanglaLLama-3-8b-BnWiki-Base support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download BanglaLLama-3-8b-BnWiki-Base GGUF?

The files are on Hugging Face in the mradermacher/BanglaLLama-3-8b-BnWiki-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 BanglaLLama-3-8b-BnWiki-Base use?

Hugging Face lists the license as llama3. 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 6.5 GB of VRAM at 8 k context, which fits within an 8 GB GPU.

Does this model support instruction following?

No, it is a causal language model only. For instruction following, use Bangla‑llama‑7b‑instruct.

Is the model detoxified?

No, the model has not undergone detoxification. Use it with supervision in sensitive contexts.

Other GGUFs of BanglaLLama-3-8b-BnWiki-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Banglallama models

All Banglallama →

Other small models

All small models →