# saraiki-libero-smolvla by Muhammad Farjad Ali Raza Source: https://savrn.com/models/saraiki-libero-smolvla Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve saraiki-libero-smolvla (605M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 1.2 GB | 1.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.6 GB | 0.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.3 GB | 0.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [saraiki-libero-smolvla on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/saraiki-libero-smolvla/gpus) ## Model Card By Muhammad Farjad Ali Raza, published under apache-2.0, revision 941928232031. ### Model Card for smolvla [SmolVLA](https://savrn.com/papers/smolvla-a-vision-language-action-model-for-affordable-and-efficient-robotics) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot). Learn how to train and run it in the [LeRobot smolvla guide](https://huggingface.co/docs/lerobot/main/en/smolvla), or browse the [full documentation](https://huggingface.co/docs/lerobot/index). ### Model Details - License: apache-2.0 - Fine-tuned from: [lerobot/smolvla_base](https://savrn.com/models/smolvla-base) - Robot type: panda - Cameras: image, image2 ### Inputs & Outputs The policy consumes these observation features and produces these action features. Inputs | Feature | Type | Shape | | --- | --- | --- | | observation.images.image | VISUAL | (3, 256, 256) | | observation.images.image2 | VISUAL | (3, 256, 256) | | observation.state | STATE | (8,) | Outputs | Feature | Type | Shape | | --- | --- | --- | | action | ACTION | (7,) | ### Training Dataset [Read the full model card (2,449 words)](https://savrn.com/models/saraiki-libero-smolvla/card) ## Identity and Version Repository themohal/saraiki-libero-smolvla Publisher Muhammad Farjad Ali Raza Task Robotics Modality Control Library lerobot Parameters 605M parameters Languages Not stated by the source Revision 94192823203147efb9c3dc281e2fc88d4efda3b4 First published 2026-10-01 Last updated 2026-10-05 ## Files and Weights 34 files, 7.4 GB in total. The weights are 13 files totalling 7.4 GB in safetensors. Weights13 files · 7.4 GB Configuration19 files · 75.3 KB Documentation1 file · 22.8 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | checkpoints/019000/pretrained_model/model.safetensors | Weights | 1.2 GB | 24dbf73d2942 | | checkpoints/019000/pretrained_model/policy_postprocessor_step_1_unnormalizer_processor.safetensors | Weights | 7.7 KB | acdb07d80d3a | | checkpoints/019000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 7.6 KB | bb6e5ea8250b | | checkpoints/019000/training_state/optimizer_state.safetensors | Weights | 1.9 GB | 284c1b4f7af4 | | checkpoints/019000/training_state/rng_state.safetensors | Weights | 15.7 KB | 8262698ce692 | | checkpoints/020000/pretrained_model/model.safetensors | Weights | 1.2 GB | a6b66da26da6 | | checkpoints/020000/pretrained_model/policy_postprocessor_step_1_unnormalizer_processor.safetensors | Weights | 7.7 KB | acdb07d80d3a | | checkpoints/020000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 7.6 KB | bb6e5ea8250b | | checkpoints/020000/training_state/optimizer_state.safetensors | Weights | 1.9 GB | cda9a8203eac | | checkpoints/020000/training_state/rng_state.safetensors | Weights | 15.7 KB | a61a73cb9f5a | | model.safetensors | Weights | 1.2 GB | a6b66da26da6 | | policy_postprocessor_step_1_unnormalizer_processor.safetensors | Weights | 7.7 KB | acdb07d80d3a | | policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 7.6 KB | bb6e5ea8250b | | checkpoints/019000/pretrained_model/config.json | Configuration | 2.4 KB | — | | checkpoints/019000/pretrained_model/policy_postprocessor.json | Configuration | 660 B | — | | checkpoints/019000/pretrained_model/policy_preprocessor.json | Configuration | 1.7 KB | — | | checkpoints/019000/pretrained_model/train_config.json | Configuration | 7.1 KB | — | | checkpoints/019000/training_state/optimizer_param_groups.json | Configuration | 13.7 KB | — | | checkpoints/019000/training_state/scheduler_state.json | Configuration | 256 B | — | | checkpoints/019000/training_state/training_step.json | Configuration | 66 B | — | | checkpoints/020000/pretrained_model/config.json | Configuration | 2.4 KB | — | | checkpoints/020000/pretrained_model/policy_postprocessor.json | Configuration | 660 B | — | | checkpoints/020000/pretrained_model/policy_preprocessor.json | Configuration | 1.7 KB | — | | checkpoints/020000/pretrained_model/train_config.json | Configuration | 7.1 KB | — | | checkpoints/020000/training_state/optimizer_param_groups.json | Configuration | 13.7 KB | — | | checkpoints/020000/training_state/scheduler_state.json | Configuration | 241 B | — | | checkpoints/020000/training_state/training_step.json | Configuration | 66 B | — | | config.json | Configuration | 2.4 KB | — | | eval/libero_saraiki_results.json | Configuration | 11.8 KB | — | | policy_postprocessor.json | Configuration | 660 B | — | | policy_preprocessor.json | Configuration | 1.7 KB | — | | train_config.json | Configuration | 7.1 KB | — | | README.md | Documentation | 22.8 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 7.4 GB [Download from Muhammad Farjad Ali Raza](https://huggingface.co/themohal/saraiki-libero-smolvla) Released by Muhammad Farjad Ali Raza through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [lerobot/smolvla_base](https://savrn.com/models/smolvla-base) - Described by [arXiv:2506.01844](https://savrn.com/papers/smolvla-a-vision-language-action-model-for-affordable-and-efficient-robotics) - Trained on (disclosed) themohal/saraiki-libero ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 7.4 GB | | 16-bit | 1.2 GB | | 8-bit | 0.6 GB | | 4-bit | 0.3 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About saraiki-libero-smolvla ### How much GPU memory does saraiki-libero-smolvla need? About 1.5 GB at 16-bit and 0.4 GB at 4-bit: the weights (605M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run saraiki-libero-smolvla on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use saraiki-libero-smolvla commercially? Yes. saraiki-libero-smolvla 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. ## Similar Models Model · Robotics ### [smolvla_libero](https://savrn.com/models/smolvla-libero) [Hugging Face Vision Language Action Models Research](https://savrn.com/model-publishers/huggingfacevla) SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint. Open weights apache-2.0 605M parameters lerobot [View model](https://savrn.com/models/smolvla-libero) Model · Robotics ### [Alpamayo-1.5-10B-DFlash](https://savrn.com/models/alpamayo-1-5-10b-dflash) [Z Lab](https://savrn.com/model-publishers/z-lab) Flash Vision-Language-Action Inference for Autonomous Driving DFlash draft model for z-lab/Alpamayo-1.5-10B, used by FlashDrive to accelerate the chain-of-causation reasoning of Alpamayo 1.5. DFlash (ICML 2026) uses a lightweight block-diffusion draft to propose several tokens in parallel; the target verifies each block in a single forward, preserving its output distribution. This draft is a 2-layer Qwen3-style network (block size 8) conditioned on target hidden states from layers 24/30/31/32/34. The repository also ships maskembedding.pt, the trained mask-token embedding FlashDrive appends to the target's embedding table. See the base model card and the FlashDrive repository for the full… Open weights other 470M parameters 40,960 tokens [View model](https://savrn.com/models/alpamayo-1-5-10b-dflash) Model · Robotics ### [smolvla_base](https://savrn.com/models/smolvla-base) [LeRobot](https://savrn.com/model-publishers/lerobot) SmolVLA is a compact, efficient Vision-Language-Action (VLA) model designed for affordable robotics, trainable on a single GPU and deployable on consumer hardware, while matching the performance of much larger VLAs through community-driven data. Original paper: (SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics)[https://arxiv.org/abs/2506.01844] For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=...… Open weights apache-2.0 450M parameters lerobot [View model](https://savrn.com/models/smolvla-base) Model · Robotics ### [smolvla_libero](https://savrn.com/models/smolvla-libero-2) [LeRobot](https://savrn.com/model-publishers/lerobot) SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint. Open weights apache-2.0 450M parameters lerobot [View model](https://savrn.com/models/smolvla-libero-2) Model · Robotics ### [smolvla_robotwin](https://savrn.com/models/smolvla-robotwin) [LeRobot](https://savrn.com/model-publishers/lerobot) SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint. Open weights apache-2.0 450M parameters lerobot [View model](https://savrn.com/models/smolvla-robotwin) Model · Robotics ### [smolvla-policy-test](https://savrn.com/models/smolvla-policy-test) [Hayato Nakamura](https://savrn.com/model-publishers/tron-hayato) SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot smolvla guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI… Open weights apache-2.0 450M parameters lerobot [View model](https://savrn.com/models/smolvla-policy-test) ## Muhammad Farjad Ali Raza [All models and datasets](https://savrn.com/model-publishers/themohal) ## Versions - [941928232031](https://savrn.com/models/saraiki-libero-smolvla/versions/941928232031) · current 2026-10-05 ## Explore More - [All robotics models](https://savrn.com/models/tasks/robotics) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-05. - [Hugging Face record](https://huggingface.co/themohal/saraiki-libero-smolvla) - [How the hub is built](https://savrn.com/model-hub/methodology)