prithivMLmods/CodeV-SVA-VL-9B-GGUF overview
CodeV SVA VL 9B GGUF CodeV SVA VL 9B is the 9B model in the CodeV SVA VL family alongside a 27B sibling , built on Qwen3.5 9B. These vision language models tra…
Runs locally from ~879.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| CodeV-SVA-VL-9B.BF16.gguf | GGUF | GGUF | 16.69 GB | Download |
| CodeV-SVA-VL-9B.Q3_K_L.gguf | GGUF | GGUF | 4.59 GB | Download |
| CodeV-SVA-VL-9B.Q3_K_M.gguf | GGUF | GGUF | 4.31 GB | Download |
| CodeV-SVA-VL-9B.Q4_K_M.gguf | GGUF | GGUF | 5.24 GB | Download |
| CodeV-SVA-VL-9B.Q4_K_S.gguf | GGUF | GGUF | 4.98 GB | Download |
| CodeV-SVA-VL-9B.Q5_K_M.gguf | GGUF | GGUF | 6.02 GB | Download |
| CodeV-SVA-VL-9B.Q5_K_S.gguf | GGUF | GGUF | 5.87 GB | Download |
| CodeV-SVA-VL-9B.Q6_K.gguf | GGUF | GGUF | 6.85 GB | Download |
| CodeV-SVA-VL-9B.Q8_0.gguf | GGUF | GGUF | 8.87 GB | Download |
| CodeV-SVA-VL-9B.mmproj-bf16.gguf | GGUF | BF16 | 879.0 MB | Download |
Model Details
| Model ID | prithivMLmods/CodeV-SVA-VL-9B-GGUF |
|---|---|
| Author | prithivMLmods |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | wyt2000/CodeV-SVA-VL-9B |
| Last modified | 2026-10-13T19:12:28.000Z |
Model README
---
base_model:
- wyt2000/CodeV-SVA-VL-9B
tags:
- text-generation-inference
- llama-cpp
license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
---
CodeV-SVA-VL-9B-GGUF
> CodeV-SVA-VL-9B is the 9B model in the CodeV-SVA-VL family (alongside a 27B sibling), built on Qwen3.5-9B. These vision-language models translate natural-language verification properties and waveform diagrams into SystemVerilog Assertions (SVAs) for hardware verification. On the Wave2SVA benchmark it scores 51.9 Func.@1, 79.4 Func.@16 and 82.0 Func.@32, far ahead of the base Qwen3.5-8B (16.5, 65.2, 70.0) and Qwen3.5-27B (25.4, 68.3, 74.0). Its Func.@1 is close to GPT-5.4 (53.9) and Qwen3.6-Plus (53.8), and it beats GLM-4.6V-106B-A12B on all three metrics. At Func.@16 and Func.@32 it still trails the larger proprietary and frontier models, such as Qwen3.6-Plus (89.4, 94.0), Kimi-K2.7-Code-1T-A32B (86.4, 90.0) and GLM-5V (82.8, 88.0). The 27B sibling is stronger, with 54.9 Func.@1 (best in the table) and 92.0 Func.@32. The card is brief. It names the accompanying paper, "QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis", but gives no usage instructions, training details or serving information. Its open-source plan lists the benchmark, model, evaluation code and dataset as released, with the paper and the data synthesis and training code still pending. The card does not state which license applies beyond the Apache-2.0 metadata tag.
Model Files
| File Name | Quant Type | File Size | File Link | Description |
|-----------|------------|-----------|-----------|-------------|
| CodeV-SVA-VL-9B.BF16.gguf | BF16 | 17.9 GB | Link | Full BF16 weights. Highest quality, largest file size. |
| CodeV-SVA-VL-9B.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Link | Lower quality but usable, good for low RAM availability. |
| CodeV-SVA-VL-9B.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Link | Low quality. |
| CodeV-SVA-VL-9B.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Link | Good quality, default size for most use cases, recommended. |
| CodeV-SVA-VL-9B.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Link | Slightly lower quality with more space savings, recommended. |
| CodeV-SVA-VL-9B.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Link | High quality, recommended. |
| CodeV-SVA-VL-9B.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Link | High quality, recommended. |
| CodeV-SVA-VL-9B.Q6_K.gguf | Q6_K | 7.36 GB | Link | Very high quality, near perfect, recommended. |
| CodeV-SVA-VL-9B.Q8_0.gguf | Q8_0 | 9.53 GB | Link | Extremely high quality, generally unneeded but max available quant. |
| CodeV-SVA-VL-9B.mmproj-bf16.gguf | mmproj-bf16 | 922 MB | Link | Multimodal projection file in BF16 format. Used for vision/language models. |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Run prithivMLmods/CodeV-SVA-VL-9B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models