LightOnOCR-3 0.8B has 0.853 billion total parameters. The selected Q4_K_M GGUF file is 0.529 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
LightOn
Total parameters
852,985,920
Exact file size
529,297,952 bytes
Quantization / precision
Q4_K_M
Weight repository
mradermacher/LightOnOCR-3-0.8B-GGUF
Original model repository
lightonai/LightOnOCR-3-0.8B
Weight revision
d76992384e501892b4e37bd55020d762d30b5b37
Model revision
4a953edfc77f0e435532c503dd69dd74663d44c3
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-07
Date evidence
Official source checkpoint created 7 October 2026; publisher announcement and model card finalized 8 October; first complete static GGUF conversion created 9 October 2026.
These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.
olmOCR-Bench · LightOnOCR-3
85.5 / 100
Publisher-reported olmOCR-Bench score for LightOnOCR-3 with output post-processing. Specialist document-understanding benchmark; not a general intelligence or speed test.
Benchmark efficiency: 161.535 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: LightOn publisher evaluation of the official BF16 source checkpoint on olmOCR-Bench. The displayed score uses output post-processing; the official page does not disclose evaluation hardware or a pinned evaluator revision.
Publisher-run source-checkpoint result, not an independent evaluation and not a benchmark of the selected Q4_K_M file. Local image inference also needs one separate projector: Q8_0 at 115,923,776 bytes or F16 at 204,987,200 bytes. The 529,297,952-byte Q4 language-weight file excludes the projector, runtime, image tensors and context memory and does not establish device speed or compatibility. The official model supports empty-prompt transcription and `grounding`; other instructions are out of distribution.
Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.
The 0.529 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.
These complete configurations pass the initial weight-size check for the selected 0.53 GB file. Allow extra memory for context and software. Check the model’s runtime notes and your inference software before buying.
Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.
Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.
Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.
Memory matches are estimates, not tested compatibility or speed. As an Amazon Associate I earn from qualifying purchases.
Confirm model architecture and quantization support in your runner. The selected weights use 0.529 GB; this excludes context cache, runtime buffers and other programs.
These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.