GA

Gaja v2.00 i1

GajaGGUF by mradermacherUpdated 2024-12-29
Download on Hugging Face
Parameters6.87B
Context4K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

Gaja v2.00 i1 needs about 9.0 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.6 GB (IQ1_S) to 5.6 GB (Q6_K).

Gaja v2.00 i1 – a Hindi/Hinglish chat model

Gaja v2.00 i1 is a 6.87B llama-based model fine‑tuned for conversational use in Hindi and Hinglish. It is derived from SarvamAI's OpenHathi and trained on 5k chat samples. The model supports a 4096 token context window.

Good at

  • Conversational Hindi/Hinglish
  • Chat‑specific fine‑tuning
  • LLM inference via llama.cpp

Limits

  • No vision support
  • License is llama2
  • Requires 8k context for memory estimates

Best for

  • Chatbot prototypes
  • Hindi language research
  • Low‑resource inference

Who it’s for. Developers building Hindi or Hinglish chat applications, researchers testing conversational LLMs, and hobbyists experimenting with llama.cpp quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 4.2 GB
Fits Get file →
IQ1_M1.7 GB 4.4 GB
Fits Get file →
IQ2_XXS1.9 GB 4.6 GB
Fits Get file →
IQ2_XS2.1 GB 4.7 GB
Fits Get file →
IQ2_S2.3 GB 4.9 GB
Fits Get file →
Q2_K_S2.4 GB 5.0 GB
Fits Get file →
IQ2_M2.4 GB 5.1 GB
Fits Get file →
Q2_K2.6 GB 5.3 GB
Fits Get file →
IQ3_XXS2.7 GB 5.3 GB
Fits Get file →
IQ3_XS2.9 GB 5.5 GB
Fits Get file →
IQ3_S3.0 GB 5.7 GB
Fits Get file →
Q3_K_S3.0 GB 5.7 GB
Fits Get file →
IQ3_M3.2 GB 5.8 GB
Fits Get file →
Q3_K_M3.4 GB 6.0 GB
Fits Get file →
Q3_K_L3.7 GB 6.3 GB
Fits Get file →
IQ4_XS3.7 GB 6.4 GB
Fits Get file →
IQ4_NL3.9 GB 6.6 GB
Fits Get file →
Q4_03.9 GB 6.6 GB
Fits Get file →
Q4_K_S3.9 GB 6.6 GB
Fits Get file →
Q4_K_M4.2 GB 6.8 GB
Fits Get file →
Q4_14.3 GB 7.0 GB
Fits Get file →
Q5_K_S4.8 GB 7.4 GB
Tight Get file →
Q5_K_M4.9 GB 7.5 GB
Tight Get file →
Q6_K5.6 GB 8.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.6 GB file, 6.4 GB memory) or IQ1_M (1.72 GB file, 6.5 GB memory). If 12 GB VRAM is available, Q4_K_M (4.17 GB file, 9 GB memory) offers a good balance of size and performance. Larger quants such as Q6_K require 10.4 GB memory at 8k context.

What GPU do you need for Gaja v2.00 i1?

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 (3.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.6 GB file, about 10.4 GB in use).

Which Gaja v2.00 i1 quant should you choose?

Q4_K_M is the usual starting point for Gaja v2.00 i1: it balances file size and quality well. Here it is a 4.2 GB file.

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
Parameters6.87B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyGaja
Licensellama2
Downloads (HF)659
Last updated2024-12-29

Frequently asked questions about Gaja v2.00 i1

How much VRAM does Gaja v2.00 i1 need?

About 9.0 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Gaja v2.00 i1 on an 8 GB GPU?

Yes, with IQ3_M: the 3.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gaja v2.00 i1 GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.1 GB, IQ2_S is 2.3 GB, Q2_K_S is 2.4 GB and 18 more.

What context length does Gaja v2.00 i1 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 Gaja v2.00 i1 GGUF?

The files are on Hugging Face in the mradermacher/Gaja-v2.00-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 Gaja v2.00 i1 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 Gaja v2.00 i1 on 8 GB VRAM?

Yes, the IQ1_S and IQ1_M quants fit within 8 GB VRAM, using approximately 6.4–6.5 GB memory at 8k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under llama2.

Other GGUFs of Gaja-v2.00

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gaja models

All Gaja →

Other small models

All small models →