Smol-GPT is an open-weight model from Gggff123. It has 8,192-token context. Its published files total 1.1 GB.
This model was converted to GGUF format using Unsloth. - SmolLM2-135M-Instruct.Q3KM.gguf - SmolLM2-135M-Instruct.Q40.gguf - SmolLM2-135M-Instruct.Q41.gguf - SmolLM2-135M-Instruct.Q6K.gguf
Model Card
This model was converted to GGUF format using Unsloth. - SmolLM2-135M-Instruct.Q3KM.gguf - SmolLM2-135M-Instruct.Q40.gguf - SmolLM2-135M-Instruct.Q41.gguf - SmolLM2-135M-Instruct.Q6K.gguf
Excerpt from the card by Gggff123.
Configuration
- Architecture
- LlamaForCausalLM
- Context length (tokens)
- 8,192
- Layers
- 30
- Hidden size
- 576
- Feed-forward size
- 1,536
- Attention heads
- 9
- Key/value heads
- 3
- Head dimension
- 64
- Vocabulary size
- 49,153
- Stored precision
- bfloat16
- Model type
- llama
Identity and Version
- Repository
- gggff123/Smol-GPT
- Publisher
- Gggff123
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- a797a212b0cd5199f9d3ef56da34d9140df48b28
- First published
- 2026-10-12
- Last updated
- 2026-10-12
Files and Weights
11 files, 1.1 GB in total. The weights are 8 files totalling 1.1 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| SmolLM2-135M-Instruct.F16.gguf | Weights | 270.9 MB | e4d9cdd28a40 |
| SmolLM2-135M-Instruct.Q3_K_M.gguf | Weights | 93.5 MB | 0a33eacea1d0 |
| SmolLM2-135M-Instruct.Q4_0.gguf | Weights | 91.7 MB | 4672d82ab7de |
| SmolLM2-135M-Instruct.Q4_1.gguf | Weights | 98.4 MB | 83f48c2997ce |
| SmolLM2-135M-Instruct.Q4_K_M.gguf | Weights | 105.5 MB | 57ea72554dbe |
| SmolLM2-135M-Instruct.Q5_K_M.gguf | Weights | 112.1 MB | ed8c87f45bfd |
| SmolLM2-135M-Instruct.Q6_K.gguf | Weights | 138.4 MB | dc3303e02f65 |
| SmolLM2-135M-Instruct.Q8_0.gguf | Weights | 144.8 MB | 5ac3268207c6 |
| config.json | Configuration | 971 B | — |
| README.md | Documentation | 502 B | — |
| .gitattributes | Repository | 2.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.1 GB
Released by Gggff123 through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Smol-GPT
What is Smol-GPT's context length?
8,192 tokens, from the maximum position embeddings in its published configuration.