SAVRN Model Hub · Comparisons
pythia-160m vs SmolLM2-135M-Instruct
Pythia-160m has 213M parameters and SmolLM2-135M-Instruct has 135M parameters; both are released under Apache License 2.0; at 16-bit, pythia-160m needs about 0.5 GB (1x MI300X from $1.85 an hour) and SmolLM2-135M-Instruct about 0.3 GB (1x MI300X from $1.85 an hour).
| Field | pythia-160m EleutherAI/pythia-160m | SmolLM2-135M-Instruct HuggingFaceTB/SmolLM2-135M-Instruct |
|---|---|---|
| Publisher | EleutherAI | Hugging Face Smol Models Research |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 213M parameters | 135M parameters |
| Architecture | GPTNeoXForCausalLM | LlamaForCausalLM |
| Library | transformers | transformers |
| Context length | 2,048 tokens | 8,192 tokens |
| Repository size | 752.2 MB | 2.0 GB |
| Artifact formats | safetensors, pytorch | safetensors, onnx, tensorboard |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.5 GB | 0.3 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.1 GB | 0.1 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 50f5173d932e | 12fd25f77366 |
| Downloads reported by the hub | 3.5M | 1.5M |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on pythia-160m
Nobody stands up an accelerator for a model that fits in half a gigabyte, which is the point of Pythia-160m. EleutherAI built the Pythia Scaling Suite for interpretability research: eight sizes from 70M to 12B, trained on the Pile in the same order, with 154 intermediate checkpoints each. It needs 0.5 GB at 16-bit; 8-bit takes that to 0.3 GB and 4-bit to 0.1 GB. The price table bottoms out at one MI300X with 192 GB at $1.85 an hour on-demand, a floor rather than a fit. We would run it in spare memory.
Nothing on the license side slows you down: Apache 2.0 permits commercial use, modification and redistribution if you keep the license and copyright notices and state significant changes. Two checks before building on it: the 2,048 token context, and the parameter count, 213M on the listing against the 160m in the name.
SAVRN's Notes on SmolLM2-135M-Instruct
We keep a slot in every facility for very small text models, and SmolLM2-135M-Instruct from Hugging Face Smol Models Research is the kind that fills it. At 135 million parameters and 0.3 GB of memory at 16-bit, it fits on any device, and the cheapest Index host, one MI300X with 192 GB at $1.85 an hour on-demand, would hold hundreds of instances. Its work is on-device text generation: short instructions, classification, routing, the traffic you do not send to a large model. Context is 8,192 tokens, enough for a page, not a contract.
Apache 2.0 allows commercial use, and our record shows it derived from and quantized from the SmolLM2-135M base, described in arXiv:2502.02737. Before deploying, confirm the base model's terms travel with it, match the September 22, 2025 update to the version you pulled, and note the onnx export for CPU serving.
Questions
Which is larger, pythia-160m or SmolLM2-135M-Instruct?
pythia-160m (213M parameters) is larger than SmolLM2-135M-Instruct (135M parameters), by the parameter counts their publishers report.
Which is cheaper to run, pythia-160m or SmolLM2-135M-Instruct?
At 4-bit, pythia-160m fits on 1x MI300X from $1.85 an hour and SmolLM2-135M-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use pythia-160m commercially?
Yes. pythia-160m is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Can I use SmolLM2-135M-Instruct commercially?
Yes. SmolLM2-135M-Instruct is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.