SAVRN Model Hub · Comparisons
Llama-3.2-1B-Instruct vs Qwen2.5-1.5B-Instruct
Llama-3.2-1B-Instruct has 1.2B parameters and Qwen2.5-1.5B-Instruct has 1.5B parameters; Llama-3.2-1B-Instruct is released under llama3.2 and Qwen2.5-1.5B-Instruct under Apache License 2.0; at 16-bit, Llama-3.2-1B-Instruct needs about 3 GB (1x MI300X from $1.85 an hour) and Qwen2.5-1.5B-Instruct about 3.7 GB (1x MI300X from $1.85 an hour).
| Field | Llama-3.2-1B-Instruct meta-llama/Llama-3.2-1B-Instruct | Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct |
|---|---|---|
| Publisher | Meta Llama | Qwen |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 1.2B parameters | 1.5B parameters |
| Architecture | LlamaForCausalLM | Qwen2ForCausalLM |
| Library | transformers | transformers |
| Context length | Not stated | 32,768 tokens |
| Repository size | 5.0 GB | 3.1 GB |
| Artifact formats | safetensors, pytorch | safetensors |
| License | llama3.2 | apache-2.0 |
| Access | Access requested at publisher | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 3 GB | 3.7 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 | 0.9 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 9213176726f5 | 989aa7980e4c |
| Downloads reported by the hub | 6.9M | 7.2M |
| 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.
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 Qwen2.5-1.5B-Instruct
When the job is turning text into JSON, reading tables or writing past 8K tokens on a slice of a card, Qwen2.5-1.5B-Instruct is the size class to look at. Its 16-bit weights are 3.1 GB and need 3.7 GB to run; 8-bit needs 1.9 GB and 4-bit 0.9 GB. At $1.85 an hour, the cheapest Index setup is a single MI300X with 192 GB, room for more than fifty copies of the 16-bit footprint, so packing the card sets your cost per instance.
Apache 2.0 permits commercial use, changes and redistribution if the license and notices stay attached and you state significant changes. Measure the 32,768-token context against your longest input, note that it is derived from the Qwen2.5-1.5B base with weights dated September 2024, and that no host has this one on the Index yet, so the card is the only price on the table.
Questions
Which is larger, Llama-3.2-1B-Instruct or Qwen2.5-1.5B-Instruct?
Qwen2.5-1.5B-Instruct (1.5B parameters) is larger than Llama-3.2-1B-Instruct (1.2B parameters), by the parameter counts their publishers report.
Which is cheaper to run, Llama-3.2-1B-Instruct or Qwen2.5-1.5B-Instruct?
At 4-bit, Llama-3.2-1B-Instruct fits on 1x MI300X from $1.85 an hour and Qwen2.5-1.5B-Instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Qwen2.5-1.5B-Instruct commercially?
Yes. Qwen2.5-1.5B-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.