Thaki HW 27B v0.1 needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.9 GB (Q2_K) to 29.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Thaki HW 27B v0.1 – 27.3B Qwen3.8 fine‑tuned for hardware design
Thaki HW 27B v0.1 is a 27.3B parameter Qwen3.8-27B fine‑tuned with a rank‑8 LoRA for Verilog RTL. It supports reasoning, tools, and vision. The model is released under Apache‑2.0 and is intended for research and experimentation.
Good at
- Hardware design reasoning
- Tool usage
- Vision tasks
Limits
- No statistically significant improvement over base Qwen3.8-27B
- Possible regression on RTLLM
- Research preview only
Best for
- Verilog code generation
- RTL dataset research
- FPGA design assistance
Who it’s for. Researchers and developers exploring hardware‑specific language models. The model is not recommended for production use; prefer the base Qwen3.8-27B for stable performance.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.9 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_S | 12.3 GB | 14.9 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 17.2 GB | Too big | Get file → | |
| IQ4_XS | 15.4 GB | 18.1 GB | Too big | Get file → | |
| Q4_K_S | 15.8 GB | 18.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q5_K_S | 19.0 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.2 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → | |
| Q8_0 | 29.0 GB | 31.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (10.86 GB file, 13.5 GB memory at 8k context). For 12 GB VRAM, Q3_K_S (12.26 GB file, 14.9 GB memory). For 16 GB VRAM, Q4_K_M (16.81 GB file, 19.5 GB memory). Estimates are approximate.
What GPU do you need for Thaki HW 27B v0.1?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q3_K_S (12.3 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
Which Thaki HW 27B v0.1 quant should you choose?
Q4_K_M is the usual starting point for Thaki HW 27B v0.1: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 29.0 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 10.9 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 Thaki HW 27B v0.1
How much VRAM does Thaki HW 27B v0.1 need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Thaki HW 27B v0.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Thaki HW 27B v0.1 GGUF?
It depends on the quant: Q2_K is 10.9 GB, Q3_K_S is 12.3 GB, Q3_K_M is 13.5 GB, Q3_K_L is 14.6 GB, IQ4_XS is 15.4 GB, Q4_K_S is 15.8 GB and 5 more.
What context length does Thaki HW 27B v0.1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Thaki HW 27B v0.1 GGUF?
The files are on Hugging Face in the mradermacher/Thaki-HW-27B-v0.1-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 Thaki HW 27B v0.1 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 Thaki HW 27B v0.1 on 8 GB VRAM?
The Q2_K quant requires 13.5 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does the model support vision tasks?
Yes, the model includes vision capabilities as part of its detected abilities.
Is the model suitable for production use?
No, it is a research preview; production use should rely on the base Qwen3.8-27B.