HuggingFaceTB/SmolLM2-135M-Instruct-Q8-mlx
Parameters135M
Context8K
Input → outputtext → text
Licenseapache-2.0
PrecisionU32 · q8
ArchitectureLlamaForCausalLM
ReleasedNov 27, 2024
Downloads137
Based on HuggingFaceTB/SmolLM2-135M-Instruct
Other sizes and formats in the family
| Model | Params | Precision | Downloads |
|---|---|---|---|
| HuggingFaceTB/SmolLM2-1.7B-Instructquantized | 1.7B | BF16 | 221.8K |
| HuggingFaceTB/SmolLM2-1.7B-Instruct-16k | 1.7B | BF16 | 572 |
| HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlxq8 | 1.7B | U32 | 248 |
| HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUFgguf | 1.7B | – | 8.8K |
| HuggingFaceTB/SmolLM2-360M | 362M | BF16 | 385.2K |
| HuggingFaceTB/SmolLM2-360M-Instructquantized | 362M | BF16 | 238.4K |
| HuggingFaceTB/SmolLM2-360M-Instruct-Q8-mlxq8 | 362M | U32 | 110 |
| HuggingFaceTB/SmolLM2-360M-Instruct-GGUFgguf | 360M | – | 15.3K |
| HuggingFaceTB/SmolLM2-135M | 135M | BF16 | 1.6M |
| HuggingFaceTB/SmolLM2-135M-Instructquantized | 135M | BF16 | 1.6M |
This release in the news
No coverage of this exact release yet.
Recent news about SmolLM
- Oct 11, 2026 · Open-source releaseConverting dense models into Mixture-of-Experts
- Oct 7, 2026 · Research paperSemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning
- Oct 7, 2026 · Research paperBoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation
- Oct 7, 2026 · Research paperEvaluating Trajectory Features for Routing Final-Layer Attention