57 lines
1.7 KiB
Markdown
57 lines
1.7 KiB
Markdown
---
|
|
license: apache-2.0
|
|
license_link: https://huggingface.co/AS-SiliconMind/SiliconMind-V1-Qwen3-8B/blob/main/LICENSE
|
|
language:
|
|
- en
|
|
base_model:
|
|
- AS-SiliconMind/SiliconMind-V1-Qwen3-8B
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- verilog
|
|
- reasoning
|
|
- multi-agent
|
|
- gguf
|
|
- quantized
|
|
- llama.cpp
|
|
- ollama
|
|
---
|
|
|
|
# SiliconMind-V1-Qwen3-8B GGUF
|
|
|
|
GGUF quantizations of [AS-SiliconMind/SiliconMind-V1-Qwen3-8B](https://huggingface.co/AS-SiliconMind/SiliconMind-V1-Qwen3-8B), a 8B model specialized for Verilog code generation, testing, and debugging.
|
|
|
|
Quantized with [llama.cpp](https://github.com/ggml-org/llama.cpp) b7437, which compatible with Ollama v0.17.4.
|
|
|
|
## Available Quantizations
|
|
|
|
| File | Size | Description |
|
|
|------|------|-------------|
|
|
| SiliconMind-V1-Qwen3-8B-F16.gguf | 25 GB | Full precision (F16) |
|
|
| SiliconMind-V1-Qwen3-8B-Q8_0.gguf | 13 GB | 8-bit, highest quality |
|
|
| SiliconMind-V1-Qwen3-8B-Q6_K.gguf | 10 GB | 6-bit |
|
|
| SiliconMind-V1-Qwen3-8B-Q5_K_M.gguf | 8.8 GB | 5-bit medium |
|
|
| SiliconMind-V1-Qwen3-8B-Q4_K_M.gguf | 7.6 GB | 4-bit medium **(recommended)** |
|
|
| SiliconMind-V1-Qwen3-8B-Q3_K_L.gguf | 6.7 GB | 3-bit large |
|
|
| SiliconMind-V1-Qwen3-8B-Q3_K_M.gguf | 6.3 GB | 3-bit medium |
|
|
| SiliconMind-V1-Qwen3-8B-Q3_K_S.gguf | 5.7 GB | 3-bit small |
|
|
| SiliconMind-V1-Qwen3-8B-Q2_K.gguf | 5.0 GB | 2-bit, smallest |
|
|
|
|
## Usage
|
|
|
|
```bash
|
|
ollama run hf.co/thuniverse-ai/SiliconMind-V1-Qwen3-8B-GGUF
|
|
```
|
|
|
|
Example prompt:
|
|
```
|
|
I would like you to implement a module named TopModule with the following
|
|
interface. All input and output ports are one bit unless otherwise
|
|
specified.
|
|
|
|
- input in (3 bits)
|
|
- output out (2 bits)
|
|
|
|
The module should implement a "population count" circuit that counts the
|
|
number of '1's in the input vector.
|
|
```
|