JA

Javi0.3 4B

JaviGGUF by mradermacherUpdated 2026-10-27
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant2.0 GB
Quick answer

Javi0.3 4B needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.0 GB (Q2_K) to 8.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Javi0.3 4B – a 4B agent model with reasoning, tools, and vision support

Javi0.3 4B is a 4.33B parameter model based on Qwen3.5. It is fine‑tuned for agent use, with strong reasoning and tool‑use abilities. The model can also handle vision inputs, though it was not trained on images.

Good at

  • Reasoning and tool usage
  • Short, grounded answers
  • Handling tool failures

Limits

  • No loops, but can still repeat identical calls
  • Vision tower unchanged, not trained on images
  • Requires low temperature for stable tool calls

Best for

  • Agent workflows with web search
  • Coding and research assistants
  • Tool‑centric chat applications

Who it’s for. Developers building agent systems that need reliable reasoning and tool integration. The model is suitable for applications that require concise, verified answers and can benefit from vision support when combined with the base vision tower.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.0 GB 3.6 GB
Fits Get file →
Q3_K_S2.1 GB 3.7 GB
Fits Get file →
Q3_K_M2.3 GB 3.9 GB
Fits Get file →
Q3_K_L2.5 GB 4.1 GB
Fits Get file →
IQ4_XS2.6 GB 4.2 GB
Fits Get file →
Q4_K_S2.6 GB 4.2 GB
Fits Get file →
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q5_K_S3.1 GB 4.7 GB
Fits Get file →
Q5_K_M3.2 GB 4.8 GB
Fits Get file →
Q6_K3.6 GB 5.2 GB
Fits Get file →
Q8_04.6 GB 6.2 GB
Fits Get file →
F168.7 GB 10.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (2.63 GB file, ~4.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (3.16 GB file, ~4.8 GB memory) offers a good balance. For 16 GB VRAM, Q6_K (3.56 GB file, ~5.2 GB memory) provides higher quality.

What GPU do you need for Javi0.3 4B?

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 Q3_K_M (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.7 GB file, about 10.3 GB in use).

Which Javi0.3 4B quant should you choose?

Q4_K_M is the usual starting point for Javi0.3 4B: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.6 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 2.0 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

Architectureqwen35
Parameters4.33B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bymradermacher
FamilyJavi
Licenseapache-2.0
Downloads (HF)1,005
Last updated2026-10-27

Frequently asked questions about Javi0.3 4B

How much VRAM does Javi0.3 4B need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Javi0.3 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Javi0.3 4B GGUF?

It depends on the quant: Q2_K is 2.0 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.5 GB, IQ4_XS is 2.6 GB, Q4_K_S is 2.6 GB and 6 more.

What context length does Javi0.3 4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Javi0.3 4B GGUF?

The files are on Hugging Face in the mradermacher/Javi0.3-4B-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 Javi0.3 4B 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 Javi0.3 4B on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires about 4.2 GB of VRAM at 8k context.

Does the model support vision?

It includes a vision tower, but it was not trained or evaluated on images.

What temperature should I use for tool calls?

Use a low temperature such as 0.2 with top‑p 0.8 and top‑k 20 for stable tool calls.

Other GGUFs of Javi0.3-4B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Javi models

All Javi →

Other small models

All small models →