rudra 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.
Rudra – a 4.33B Qwen3.5-4B fine‑tuned for autonomous agent loops
Rudra is a LoRA fine‑tune of Qwen3.5-4B trained to run autonomous agent loops with strict, machine‑parsable JSON envelopes. It is optimized for agentic workflows, function calling, tool use, structured output, and anti‑hallucination behavior on consumer hardware.
Good at
- Strict JSON envelope output
- 100% tool‑call accuracy
- Phantom‑proof agent loops
Limits
- Requires 8‑k context for memory estimates
- No vision support
- License is apache‑2.0
Best for
- File‑operation agents
- Tool‑using coding tasks
- Structured output generation
Who it’s for. Developers building autonomous agents that need reliable tool invocation and structured JSON output. Suitable for users with consumer GPUs such as RTX 3050 6 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.6 GB | 6.2 GB | Fits | Get file → | |
| F16 | 8.7 GB | 10.3 GB | Too big | Get file → |
For 6 GB VRAM, use Q8_0 (4.61 GB) or Q6_K (3.56 GB). If memory is tighter, Q4_K_M (2.78 GB) or Q5_K_M (3.16 GB) provide a balance between size and performance. All estimates are approximate.
What GPU do you need for rudra?
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 rudra quant should you choose?
Q4_K_M is the usual starting point for rudra: 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
Source
Frequently asked questions about rudra
How much VRAM does rudra 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 rudra 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 rudra 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 rudra 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 rudra GGUF?
The files are on Hugging Face in the mradermacher/rudra-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 rudra 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 Rudra on 6 GB VRAM?
Yes, the Q8_0 quant (4.61 GB) fits in 6 GB VRAM and runs fully in GPU memory.
Does Rudra support vision?
No, Rudra does not have vision capabilities.