Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned needs about 10.9 GB of memory at Q4_K_M (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 11.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned – a 13.6B dense model
Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned is a 13.6B parameter dense model built from Qwen3-8B and Qwen3-235B-A22* MoE. It interleaves transformer blocks to create a larger dense architecture while keeping the Qwen3-8B tokenizer and base configuration.
Good at
- Reasoning
- Tool usage
- Large context (40960 tokens)
Limits
- No fine‑tuning performed
- No vision support
- License: apache-2.0
Best for
- Research on layer‑interleaved composites
- Experimentation with dense MoE conversion
- Testing large‑context models
Who it’s for. Researchers and developers interested in dense model construction from MoE sources. Suitable for experimentation and proof‑of‑concept work rather than production deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| IQ1_S | 3.3 GB | 5.9 GB | Fits | Get file → | |
| IQ1_M | 3.5 GB | 6.2 GB | Fits | Get file → | |
| IQ2_XXS | 3.9 GB | 6.6 GB | Fits | Get file → | |
| IQ2_XS | 4.3 GB | 6.9 GB | Fits | Get file → | |
| IQ2_S | 4.6 GB | 7.2 GB | Tight | Get file → | |
| IQ2_M | 4.9 GB | 7.5 GB | Tight | Get file → | |
| Q2_K_S | 4.9 GB | 7.6 GB | Tight | Get file → | |
| Q2_K | 5.3 GB | 7.9 GB | Tight | Get file → | |
| IQ3_XXS | 5.4 GB | 8.1 GB | Too big | Get file → | |
| IQ3_XS | 5.8 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_S | 6.1 GB | 8.7 GB | Too big | Get file → | |
| IQ3_S | 6.1 GB | 8.8 GB | Too big | Get file → | |
| IQ3_M | 6.3 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_M | 6.7 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_L | 7.3 GB | 9.9 GB | Too big | Get file → | |
| IQ4_XS | 7.5 GB | 10.1 GB | Too big | Get file → | |
| Q4_0 | 7.8 GB | 10.5 GB | Too big | Get file → | |
| IQ4_NL | 7.8 GB | 10.5 GB | Too big | Get file → | |
| Q4_K_S | 7.9 GB | 10.5 GB | Too big | Get file → | |
| Q4_K_M | 8.3 GB | 10.9 GB | Too big | Get file → | |
| Q4_1 | 8.6 GB | 11.3 GB | Too big | Get file → | |
| Q5_K_S | 9.4 GB | 12.1 GB | Too big | Get file → | |
| Q5_K_M | 9.7 GB | 12.3 GB | Too big | Get file → | |
| Q6_K | 11.2 GB | 13.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3.27 GB, 5.9 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (4.3 GB, 6.9 GB memory) or Q4_K_M (8.26 GB, 10.9 GB memory). Larger VRAM allows Q5_K_M or Q6_K for higher quality.
What GPU do you need for Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned?
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 the main file (0.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_S (3.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K (5.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (8.6 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.2 GB file, about 13.8 GB in use).
Which Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned quant should you choose?
Q4_K_M is the usual starting point for Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned: it balances file size and quality well. Here it is a 8.3 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned
How much VRAM does Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned need?
About 10.9 GB at Q4_K_M with an 8K context window. That is the 8.3 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 Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned on an 8 GB GPU?
Yes, with Q2_K: the 5.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.3 GB, IQ2_S is 4.6 GB and 19 more.
What context length does Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned GGUF?
The files are on Hugging Face in the mradermacher/frankenqwen3-8B-235B-dense-conversion-interleaved-untuned-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 Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned 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 this model on 8 GB VRAM?
Yes, use the IQ1_S quant which requires about 5.9 GB memory at 8k context.
Does this model support vision?
No, it only supports text.
Is the model fine‑tuned?
No, it has not been fine‑tuned after conversion.