G9

G9v3 3B

GGUFGGUF by WhiskyAKMUpdated 2026-08-01
Download on Hugging Face
Parameters2.99B
Context128K
Layers52
Architecturellama
Smallest quant1.8 GB
Quick answer

G9v3 3B needs about 2.8 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 1.8 GB (Q4_0) to 6.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Compact 3B Llama model with 128K context and tool‑calling

G9v3-3B is a dense 3B‑parameter causal language model built for local deployment. It supports a 131,072‑token context window, reasoning tokens, and XML‑style tool calling. The model is released under Apache‑2.0.

Good at

  • Reasoning with /think tokens
  • Tool‑calling via XML tags
  • Large 128K context window

Limits

  • No vision support
  • Requires 8K context for memory estimates
  • No GPU‑specific optimizations listed

Best for

  • Local assistant tasks
  • Coding help with tool integration
  • Long‑form reasoning

Who it’s for. Developers and researchers needing a lightweight Llama model for local inference. Suitable for environments with limited GPU memory and where tool‑calling or extended reasoning is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.8 GB 2.7 GB
Fits Get file →
Q4_K_S1.8 GB 2.7 GB
Fits Get file →
Q4_K_M1.8 GB 2.8 GB
Fits Get file →
Q5_K_S2.1 GB 3.0 GB
Fits Get file →
Q5_K_M2.1 GB 3.1 GB
Fits Get file →
Q6_K2.5 GB 3.4 GB
Fits Get file →
Q8_03.2 GB 4.1 GB
Fits Get file →
BF166.0 GB 6.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.84 GB file, ~2.8 GB memory). For 12 GB VRAM, Q5_K_M (2.14 GB file, ~3.1 GB memory) offers better quality. BF16 requires ~6.9 GB memory and is only for higher‑end GPUs.

What GPU do you need for G9v3 3B?

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 Q6_K (2.5 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.0 GB file, about 6.9 GB in use).

Which G9v3 3B quant should you choose?

Q4_K_M is the usual starting point for G9v3 3B: it balances file size and quality well. Here it is a 1.8 GB file.

The Q8_0 file is 3.2 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 Q4_0 at 1.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.99B
Layers52
Trained context131,072 tokens
KV cache (fp16)52 KB per token

Source

Quantized byWhiskyAKM
Licenseapache-2.0
Downloads (HF)695
Last updated2026-08-01

Frequently asked questions about G9v3 3B

How much VRAM does G9v3 3B need?

About 2.8 GB at Q4_K_M with an 8K context window. That is the 1.8 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 G9v3 3B on an 8 GB GPU?

Yes, with BF16: the 6.0 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of G9v3 3B GGUF?

It depends on the quant: Q4_0 is 1.8 GB, Q4_K_S is 1.8 GB, Q4_K_M is 1.8 GB, Q5_K_S is 2.1 GB, Q5_K_M is 2.1 GB, Q6_K is 2.5 GB and 2 more.

What context length does G9v3 3B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download G9v3 3B GGUF?

The files are on Hugging Face in the WhiskyAKM/G9v3-3B-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 G9v3 3B 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 G9v3-3B on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 2.8 GB of VRAM at 8K context, which fits within 8 GB.

Does G9v3-3B support vision?

No, the model only handles text and does not include vision capabilities.

Other GGUFs of G9v3-3B

Similar models

Browse all →

More from WhiskyAKM

All by WhiskyAKM →

Other tiny models

All tiny models →