SAVRN Model Hub · Comparisons
Llama-3.2-1B-Instruct vs OpenELM-1_1B-Instruct
Llama-3.2-1B-Instruct has 1.2B parameters and OpenELM-1_1B-Instruct has 1.1B parameters; Llama-3.2-1B-Instruct is released under llama3.2 and OpenELM-1_1B-Instruct under apple-amlr; at 16-bit, Llama-3.2-1B-Instruct needs about 3 GB (1x MI300X from $1.85 an hour) and OpenELM-1_1B-Instruct about 2.6 GB (1x MI300X from $1.85 an hour).
| Field | Llama-3.2-1B-Instruct meta-llama/Llama-3.2-1B-Instruct | OpenELM-1_1B-Instruct apple/OpenELM-1_1B-Instruct |
|---|---|---|
| Publisher | Meta Llama | Apple |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 1.2B parameters | 1.1B parameters |
| Architecture | LlamaForCausalLM | OpenELMForCausalLM |
| Library | transformers | transformers |
| Context length | Not stated | Not stated |
| Repository size | 5.0 GB | 2.2 GB |
| Artifact formats | safetensors, pytorch | safetensors |
| License | llama3.2 | apple-amlr |
| Access | Access requested at publisher | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 3 GB | 2.6 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.7 GB | 0.6 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 9213176726f5 | effd796da2a7 |
| Downloads reported by the hub | 6.9M | 1.4M |
| Last observed | 2026-09-19 | 2026-09-19 |
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.
Other Reported Results
These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.
Llama-3.2-1B-Instruct
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| Idavidrein/gpqa | Task diamondMetric diamondSetup GPQA DiamondComparison conditions not established | 18.6869 | EvalEval Reported by a third party |
Evaluated revision not stated | 2026-04-16 |
SAVRN's Notes on Llama-3.2-1B-Instruct
We would run this as the small worker on a card already doing something else. Meta's instruction-tuned 1B is the smaller of the two Llama 3.2 sizes, tuned for multilingual dialogue, retrieval and summarization. At 16-bit it needs 3.0 GB to run, and the cheapest setup we list, one MI300X with 192 GB at $1.85 an hour on demand, is far more card than it needs; 4-bit takes it to 0.7 GB.
The license is Meta's own, llama3.2, not Apache or MIT, with no summary in our file; read it in full before you deploy. Access is gated: you request it from the publisher and accept the terms before the weights come down. The context length is not recorded here; confirm it with the publisher, and weigh the 3B sibling before you size. One attached paper covers SpinQuant quantization; read it before running at 4-bit.
SAVRN's Notes on OpenELM-1_1B-Instruct
Read the license before the spec sheet on this one. Apple releases it under its own apple-amlr terms, and our facts file carries no summary of what they permit, so legal reads the full text before anyone loads a weight. The hardware question is easy: 1.1 billion parameters need 2.6 GB of memory at 16-bit, 1.3 GB at 8-bit and 0.6 GB at 4-bit, so the cheapest card we price, a 192 GB MI300X at $1.85 an hour, would sit nearly empty serving it alone. It belongs on a shared card with other small models, not on a GPU of its own.
Two gaps to check. No context length is published, so test the input size you need before designing a prompt around it. No host on the SAVRN Index serves it, so there is no rental price to beat; the choice is run it yourself or not at all. Apple ships 270M, 450M, 1.1B and 3B sizes along with the CoreNet training framework, described in arXiv:2404.14619, so the training path is open if you want to adapt it.
Questions
Which is larger, Llama-3.2-1B-Instruct or OpenELM-1_1B-Instruct?
Llama-3.2-1B-Instruct (1.2B parameters) is larger than OpenELM-1_1B-Instruct (1.1B parameters), by the parameter counts their publishers report.
Which is cheaper to run, Llama-3.2-1B-Instruct or OpenELM-1_1B-Instruct?
At 4-bit, Llama-3.2-1B-Instruct fits on 1x MI300X from $1.85 an hour and OpenELM-1_1B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.