# qwen3-vl-8b-hebrew-v20a-merged by Isaac Godfried: Open Model Source: https://savrn.com/models/qwen3-vl-8b-hebrew-v20a-merged Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve qwen3-vl-8b-hebrew-v20a-merged (8.8B 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 | 17.5 GB | 21.0 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 | 8.8 GB | 10.5 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 | | 4-bit | 4.4 GB | 5.3 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 12, 2026. [qwen3-vl-8b-hebrew-v20a-merged on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen3-vl-8b-hebrew-v20a-merged/gpus) ## Model Card By Isaac Godfried, published under apache-2.0, revision 48a0e3993f1b. ### Qwen3-VL-8B Hebrew v2.0a — merged weights (step 1800) [Cairo Genizah AI Transcription — formal analysis and write-up of the project](https://medium.com/deep-data-science/transcribing-the-cairo-genizah-with-multi-modal-ai-ad4cd9cbe980) The full account of the methods, training data, benchmarks and error analysis behind the Cairo Genizah AI transcription models. Search the transcribed corpus at [Cairo Genizah AI](https://cairogenizah.ai). Merged bf16 weights of the v2.0a checkpoint ([v20a-ckpt](https://savrn.com/models/qwen3-vl-8b-hebrew-v20a-ckpt), step 1800, commit af9df6a0): the LoRA adapters (language layers r16, vision tower) folded into Qwen3-VL-8B-Instruct. Ready for transformers, vLLM, or conversion. The image processor ships the model's resolution contract (min_pixels=6_500_000, max_pixels=7_000_000): send the largest image you have and let the processor resize it. Status: current best of the series on both transcription benchmarks (Sep 2026) and the first checkpoint with text grounding. Serving demo: the Genizah Reader Space. ### What it does [Read the full model card (510 words)](https://savrn.com/models/qwen3-vl-8b-hebrew-v20a-merged/card) ## Configuration Architecture Qwen3VLForConditionalGeneration Context length (tokens) 262,144 Layers 36 Hidden size 4,096 Feed-forward size 12,288 Attention heads 32 Key/value heads 8 Head dimension 128 Vocabulary size 151,936 RoPE base 5,000,000 Model type qwen3_vl ## Identity and Version Repository isaacmg/qwen3-vl-8b-hebrew-v20a-merged Publisher Isaac Godfried Task Image and text to text Modality Image and text Library transformers Parameters 8.8B parameters Languages he Revision 48a0e3993f1b7b3a057901b5d24fba0648e6dbfc First published 2026-09-10 Last updated 2026-10-05 ## Files and Weights 18 files, 17.6 GB in total. The weights are 4 files totalling 17.5 GB in safetensors. Weights4 files · 17.5 GB Configuration7 files · 72.5 KB Tokenizer4 files · 15.9 MB Documentation1 file · 4.6 KB Other1 file · 5.3 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00004.safetensors | Weights | 5.0 GB | 398fd584a0d4 | | model-00002-of-00004.safetensors | Weights | 4.9 GB | 676af639d1cb | | model-00003-of-00004.safetensors | Weights | 4.9 GB | a49f612eefab | | model-00004-of-00004.safetensors | Weights | 2.7 GB | 8e0ea4b4bf4b | | added_tokens.json | Configuration | 707 B | — | | config.json | Configuration | 1.5 KB | — | | generation_config.json | Configuration | 213 B | — | | model.safetensors.index.json | Configuration | 67.8 KB | — | | preprocessor_config.json | Configuration | 788 B | — | | special_tokens_map.json | Configuration | 613 B | — | | video_preprocessor_config.json | Configuration | 817 B | — | | README.md | Documentation | 4.6 KB | — | | chat_template.jinja | Other | 5.3 KB | — | | .gitattributes | Repository | 1.6 KB | — | | merges.txt | Tokenizer | 1.7 MB | — | | tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a | | tokenizer_config.json | Tokenizer | 5.4 KB | — | | vocab.json | Tokenizer | 2.8 MB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 17.5 GB [Download from Isaac Godfried](https://huggingface.co/isaacmg/qwen3-vl-8b-hebrew-v20a-merged) Released by Isaac Godfried through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [Qwen/Qwen3-VL-8B-Instruct](https://savrn.com/models/qwen3-vl-8b-instruct) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 17.5 GB | | 16-bit | 17.5 GB | | 8-bit | 8.8 GB | | 4-bit | 4.4 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About qwen3-vl-8b-hebrew-v20a-merged ### How much GPU memory does qwen3-vl-8b-hebrew-v20a-merged need? About 21 GB at 16-bit and 5.3 GB at 4-bit: the weights (8.8B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run qwen3-vl-8b-hebrew-v20a-merged 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 qwen3-vl-8b-hebrew-v20a-merged commercially? Yes. qwen3-vl-8b-hebrew-v20a-merged 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. ### What is qwen3-vl-8b-hebrew-v20a-merged's context length? 262,144 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Image and text to text ### [Qwen3-VL-8B-Instruct](https://savrn.com/models/qwen3-vl-8b-instruct) [Qwen](https://savrn.com/model-publishers/qwen) Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment. Text Understanding on par with pure LLMs: Seamless text–vision fusion for lossless, unified comprehension. 1. Interleaved-MRoPE: Full‑frequency allocation over time, width, and height… Open weights apache-2.0 8.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-vl-8b-instruct) Model · Image and text to text ### [qwen3-vl-8b-hebrew-rashi-merged](https://savrn.com/models/qwen3-vl-8b-hebrew-rashi-merged) [Isaac Godfried](https://savrn.com/model-publishers/isaacmg) This is a historical merged export, NOT the current flagship. The flagship is v1.9a — adapter + merge instructions at qwen3-vl-8b-hebrew-v19a-ckpt. Full 16-bit merge of v1.5, the Rashi-script generation: pure Rashi glyph perception proven (CER 0.018 on unmemorizable synthetic text), crop-level Vilna gemara solved (CER 0.019), Talmud page-level gemara CER 0.059. Trained at a 3.2 MP resolution floor — use that policy at inference. Vision tower unadapted. Superseded by v1.6+ on print and v1.9a on manuscripts. One line per generation — which checkpoint to use and which are historical: \\ CER over substantive attempts only, alignment-based scorer. Benchmarks differ across generations (Talmud… Open weights apache-2.0 8.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-vl-8b-hebrew-rashi-merged) Model · Image and text to text ### [qwen3-vl-8b-hebrew-merged](https://savrn.com/models/qwen3-vl-8b-hebrew-merged) [Isaac Godfried](https://savrn.com/model-publishers/isaacmg) This is a historical merged export, NOT the current flagship. The flagship is v1.9a — adapter + merge instructions at qwen3-vl-8b-hebrew-v19a-ckpt. Full 16-bit merge of the series' first-generation (v1) Talmud adapter — the first model in this line to read Vilna-print gemara from pixels. Vision tower unadapted (language-only LoRA generation). Superseded on every (rope under textconfig.ropeparameters); MLX conversion requires patching ropetheta to top level. One line per generation — which checkpoint to use and which are historical: \\ CER over substantive attempts only, alignment-based scorer. Benchmarks differ across generations (Talmud print vs Genizah manuscripts) — compare within a… Open weights apache-2.0 8.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-vl-8b-hebrew-merged) Model · Image and text to text ### [MemGUI-8B-RL](https://savrn.com/models/memgui-8b-rl) [Anonymous](https://savrn.com/model-publishers/memgui-rl) Anonymous release for the ICLR 2027 submission MemGUI-RL: Reinforcement Learning for Proactive Context Management in Long-Horizon Mobile GUI Agents. Project page: https://memgui-rl-anonymous.github.io/ MemGUI-8B-RL is MemGUI-8B-SFT (Qwen3-VL-8B-Instruct supervised on MemGUI-3K) post-trained for 100 optimizer steps with FARPO (Folding-Aware Reward-decoupled Policy Optimization, span-to-step ratio rho = 9). The policy speaks the ConAct (Context-as-Action) interface of MemGUI-Agent: every response contains a folding directive for its own history, an optional memory operation and the next GUI action. The checkpoint is a standard Qwen3VLForConditionalGeneration model (weights in bf16, ~17.5 GB).… Open weights apache-2.0 8.8B parameters 262,144 tokens [View model](https://savrn.com/models/memgui-8b-rl) Model · Image and text to text ### [Legend_ocr_qwen3-highavg](https://savrn.com/models/legend-ocr-qwen3-highavg) [Jackson Kahungu](https://savrn.com/model-publishers/keystats) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 8.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/legend-ocr-qwen3-highavg) Model · Image and text to text ### [Qwen3-VL-8B-Instruct-FP8](https://savrn.com/models/qwen3-vl-8b-instruct-fp8) [Qwen](https://savrn.com/model-publishers/qwen) Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment. Text Understanding on par with pure LLMs: Seamless text–vision fusion for lossless, unified comprehension. 1. Interleaved-MRoPE: Full‑frequency allocation over time, width, and height… Open weights apache-2.0 8.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-vl-8b-instruct-fp8) ## Isaac Godfried [All models and datasets](https://savrn.com/model-publishers/isaacmg) ## Versions - [48a0e3993f1b](https://savrn.com/models/qwen3-vl-8b-hebrew-v20a-merged/versions/48a0e3993f1b) · current 2026-10-05 ## Explore More - [All image and text to text models](https://savrn.com/models/tasks/image-and-text-to-text) - [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/isaacmg/qwen3-vl-8b-hebrew-v20a-merged) - [How the hub is built](https://savrn.com/model-hub/methodology)