QW

Bharat Tiny LLM v3

QwenGGUF by eulogikUpdated 2026-09-23
Download on Hugging Face
Parameters1.72B
Context32K
Layers28
Architectureqwen3
Smallest quant1.1 GB
Quick answer

Bharat Tiny LLM v3 needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 1.1 GB (Q4_K_M) to 3.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Bharat Tiny LLM v3 – a 1.7B Hindi/Hinglish/English model for edge devices

Bharat Tiny LLM v3 is a 1.7‑billion‑parameter small language model built on Qwen3‑1.7B‑Base. It is fine‑tuned for Hindi, Hinglish, and English and runs fully offline on phones, laptops, or browsers. The model is released under Apache‑2.0 and ships as a 1.11 GB GGUF file.

Good at

  • Hindi and Hinglish text generation
  • Offline inference on low‑resource devices
  • Tool‑aware responses

Limits

  • No vision support
  • Context limited to 32,768 tokens
  • Requires 8 k context memory estimate of 2.5 GB for Q4_K_M

Best for

  • Edge‑device chat assistants
  • Local Hindi language tutoring
  • Browser‑based LLM demos

Who it’s for. Developers and hobbyists needing a lightweight Hindi/Hinglish/English LLM that can run without internet access. The model is suitable for mobile apps, offline tools, and web demos that require local inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
F163.4 GB 4.9 GB
Fits Get file →
F163.4 GB 4.9 GB
Fits Get file →
F163.4 GB 4.9 GB
Fits Get file →
F163.4 GB 4.9 GB
Fits Get file →

For 8 GB VRAM, the Q4_K_M quantization (1.11 GB file, ~2.5 GB memory at 8 k context) is recommended. If more VRAM is available, the F16 quant (3.45 GB file, ~4.9 GB memory) offers higher precision.

What GPU do you need for Bharat Tiny LLM v3?

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 Q4_K_M (1.1 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).

Which Bharat Tiny LLM v3 quant should you choose?

Q4_K_M is the usual starting point for Bharat Tiny LLM v3: it balances file size and quality well. Here it is a 1.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters1.72B
Layers28
Trained context32,768 tokens
KV cache (fp16)112 KB per token

Source

Quantized byeulogik
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,042
Last updated2026-09-23

Frequently asked questions about Bharat Tiny LLM v3

How much VRAM does Bharat Tiny LLM v3 need?

About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Bharat Tiny LLM v3 on an 8 GB GPU?

Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bharat Tiny LLM v3 GGUF?

It depends on the quant: Q4_K_M is 1.1 GB, Q4_K_M is 1.1 GB, Q4_K_M is 1.1 GB, Q4_K_M is 1.1 GB, F16 is 3.4 GB, F16 is 3.4 GB and 2 more.

What context length does Bharat Tiny LLM v3 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Bharat Tiny LLM v3 GGUF?

The files are on Hugging Face in the eulogik/Bharat-Tiny-LLM-v3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Bharat Tiny LLM v3 use?

Hugging Face lists the license as apache-2.0. 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 Bharat Tiny LLM v3 on a device with 8 GB VRAM?

Yes, the Q4_K_M GGUF file is 1.11 GB and requires approximately 2.5 GB of VRAM at 8 k context, which fits within 8 GB.

Does Bharat Tiny LLM v3 support image input?

No, the model does not have vision capabilities.

What license applies to Bharat Tiny LLM v3?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3-1.7B-Base

Similar models

Browse all →

More from eulogik

All by eulogik →

More Qwen models

All Qwen →

Other tiny models

All tiny models →