SmolLM-135M-Instruct-FP32
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Params
135 M
Context
2,048
Downloads 30d
143 K
Likes
0
Download history
tracking started — chart appears after 7 days of snapshots (1 recorded)143 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 0.5 GB | 1.1 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/smollm-135m-instruct-fp32
{
"hf_id": "modularai/SmolLM-135M-Instruct-FP32",
"params_b": 0.13,
"context_length": 2048,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 143038,
"vram_estimates": [
{ "quant": "f32", "gb": 1.1 }
],
"updated_at": "2026-10-25T01:00:29Z"
}
Specifications
- Architecture
- LlamaForCausalLM
- Parameters
- 135 M
- Tensor type
- F32
- Context length
- 2,048
- Vocabulary
- 49,152
- Layers / heads
- 30 / 9
- First seen on the Hub
- 2025-07-31
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-25
Compare with any text-generation model