CodeV SVA VL 27B needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.7 GB (Q2_K) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
CodeV SVA VL 27B – Vision‑language model for automated hardware assertion generation
CodeV SVA VL 27B is a 26.9 billion‑parameter vision‑language model based on the qwen35 architecture. It translates natural‑language verification properties and waveform diagrams into SystemVerilog Assertions. The model is released under the Apache‑2.0 license.
Good at
- Vision‑language reasoning
- Tools integration
- Hardware assertion generation
Limits
- Requires large VRAM – smallest quant needs 13.4 GB at 8 k context
- No support for audio or text‑only tasks beyond vision
- No mixed‑precision quant available
Best for
- Generating SystemVerilog Assertions from diagrams
- Automated hardware verification workflows
- Research on vision‑language models for EDA
Who it’s for. Engineers and researchers working on hardware verification who need to convert natural‑language specifications and waveform images into SystemVerilog Assertions. The model is suitable for academic projects and industrial R&D where open‑source licensing is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.7 GB | 13.4 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 14.8 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 16.0 GB | Too big | Get file → | |
| Q3_K_L | 14.3 GB | 17.0 GB | Too big | Get file → | |
| IQ4_XS | 15.2 GB | 17.9 GB | Too big | Get file → | |
| Q4_K_S | 15.6 GB | 18.3 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 19.2 GB | Too big | Get file → | |
| Q5_K_S | 18.7 GB | 21.4 GB | Too big | Get file → | |
| Q5_K_M | 19.2 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.8 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.3 GB | Too big | Get file → |
For a 16 GB VRAM setup, Q2_K (10.71 GB file, 13.4 GB memory) is a good starting point. If 24 GB VRAM is available, Q4_K_M (16.55 GB file, 19.2 GB memory) offers higher quality. Larger quants such as Q8_0 (28.6 GB file, 31.3 GB memory) require 32 GB or more and provide the best fidelity.
What GPU do you need for CodeV SVA VL 27B?
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_M (13.3 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.3 GB in use).
Which CodeV SVA VL 27B quant should you choose?
Q4_K_M is the usual starting point for CodeV SVA VL 27B: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.6 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 10.7 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 CodeV SVA VL 27B
How much VRAM does CodeV SVA VL 27B need?
About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 CodeV SVA VL 27B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of CodeV SVA VL 27B GGUF?
It depends on the quant: Q2_K is 10.7 GB, Q3_K_S is 12.1 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.2 GB, Q4_K_S is 15.6 GB and 5 more.
What context length does CodeV SVA VL 27B 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 CodeV SVA VL 27B GGUF?
The files are on Hugging Face in the mradermacher/CodeV-SVA-VL-27B-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 CodeV SVA VL 27B 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?
No. The smallest quant requires 13.4 GB of VRAM at 8 k context.
Does the model support vision tasks?
Yes, it is designed for vision‑language reasoning and can process waveform diagrams.
What license does the model use?
The model is released under the Apache‑2.0 license.