LLM Name | Seed Coder 8B Reasoning Mlx Fp16 |
Repository π€ | https://huggingface.co/cnfusion/Seed-Coder-8B-Reasoning-mlx-fp16 |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 16.5 GB |
Updated | 2025-06-09 |
Maintainer | cnfusion |
Model Type | llama |
Model Files | |
Quantization Type | fp16 |
Generates Code | Yes |
Model Architecture | LlamaForCausalLM |
License | mit |
Context Length | 65536 |
Model Max Length | 65536 |
Transformers Version | 4.47.1 |
Tokenizer Class | PreTrainedTokenizer |
Padding Token | <[PADβTOKEN]> |
Vocabulary Size | 155136 |
Torch Data Type | float32 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Test Dataset Codellama 3 8B | 8K / 16.1 GB | 17 | 78 |
CoolerCoder 8B Model Stock | 128K / 16.1 GB | 34 | 2 |
...ynesthesia 3.1 Task Arithmetic | 128K / 16.1 GB | 18 | 0 |
Replete Coder V2 Llama 3.1 8B | 128K / 16.1 GB | 19 | 9 |
Seed Coder 8B Reasoning | 64K / 32.9 GB | 17541 | 122 |
Seed Coder 8B Reasoning Bf16 | 64K / 16.5 GB | 6150 | 11 |
Seed Coder 8B Reasoning GGUF | 64K / 2.3 GB | 2550 | 2 |
Seed Coder 8B Instruct | 32K / 16.5 GB | 8749 | 93 |
Seed Coder 8B Base | 32K / 16.5 GB | 3173 | 45 |
Wasm Coder 8B Instruct V1 | 32K / 32.9 GB | 93 | 2 |
π Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! π