SAVRN
Search Contact SAVRN

Open-weight model · Image and text to text

qwen-vl-8b-cairo-genizah-v18a

by Isaac Godfried isaacmg/qwen-vl-8b-cairo-genizah-v18a

qwen-vl-8b-cairo-genizah-v18a is an open-weight model for image and text to text from Isaac Godfried, released under Apache License 2.0. It has 262,144-token context. Its published files total 14.8 GB. It draws 13 downloads a month.

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.

Parameters—
Context262,144
Weights14.8 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads13

Model Card

By Isaac Godfried, published under apache-2.0, revision 9e372f966e33.

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 v1.8a, the vision-frozen control arm of the v1.8 A/B experiment (its twin v1.8b trained the vision tower and won). Kept for reproducing the ablation; do not use for inference. 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 row's named benchmark, not across rows.

Read Isaac Godfried's full model card

Qwen3-VL-8B Hebrew — v1.8a merged (vision-frozen control, historical)

Cairo Genizah AI Transcription — formal analysis and write-up of the project 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.

This is a historical merged export, NOT the current flagship. The flagship isv1.9a — adapter + merge instructions at qwen3-vl-8b-hebrew-v19a-ckpt.

Full 16-bit merge of v1.8a, the vision-frozen control arm of the v1.8 A/B experiment (its twin v1.8b trained the vision tower and won). Kept for reproducing the ablation; do not use for inference.

The series at a glance

One line per generation — which checkpoint to use and which are historical:

version repo status canonical revision headline (benchmark)
v1.9a v19a-ckpt FLAGSHIP — use this step 1300 43e21bd7 F1 0.816 / CER 0.216 (Genizah religious-140); F1 0.862 / CER 0.196 (frozen PGP-131)
v1.9b v19b-ckpt experimental control — not adopted step 1300 f8618c28 merger-LoRA ablation study; loss ≡ v1.9a
v1.8b v18b-ckpt superseded; warm-start ancestor of all v1.9 step 700 c80313f8 first arm with a live vision-tower LoRA
v1.8a v18a-ckpt superseded A/B control (vision frozen) step 700 control arm for the v1.8 vision experiment
v1.7 v17-ckpt superseded step 800 first Genizah-handwriting generation; best VLM on both corpora at its era's benchmarks (Aug 2026)
v1.6 v16-ckpt superseded; Talmud-print reference step 1000 (official); step 1100 b9f47f32 (v1.7 warm start) Talmud page CER: gemara 0.090 / rashi 0.047 / tosafot 0.099 — Rashi-script 6.7× better than the best closed model we tested (0.315)
v1.5 rashi-ckpt superseded final e050aca8 (step 2000) proved pure Rashi-glyph perception: CER 0.018 on unmemorizable synthetic text
v1 hebrew-ckpt superseded (language-only LoRA) step 3800 e2f85dde first checkpoints to read Vilna gemara from pixels

\* CER over substantive attempts only, alignment-based scorer. Benchmarks differ across generations (Talmud print vs Genizah manuscripts) — compare within a row's named benchmark, not across rows.

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
Stored precision
bfloat16
Model type
qwen3_vl

Identity and Version

Repository
isaacmg/qwen-vl-8b-cairo-genizah-v18a
Publisher
Isaac Godfried
Task
Image and text to text
Modality
Image and text
Library
transformers
Parameters
Not stated by the source
Languages
he
Revision
9e372f966e330ec27b552ed086d82183f9502906
First published
2026-08-10
Last updated
2026-10-05

Files and Weights

17 files, 14.8 GB in total. The weights are 3 files totalling 14.8 GB in safetensors.

Weights3 files · 14.8 GB
Configuration7 files · 72.8 KB
Tokenizer4 files · 15.9 MB
Documentation1 file · 3.3 KB
Other1 file · 5.3 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00004.safetensorsWeights4.9 GB a210ce297111
model-00002-of-00004.safetensorsWeights4.9 GB fe197f600f37
model-00003-of-00004.safetensorsWeights5.0 GB 37c62468c078
added_tokens.jsonConfiguration707 B —
config.jsonConfiguration1.9 KB —
generation_config.jsonConfiguration187 B —
model.safetensors.index.jsonConfiguration67.8 KB —
preprocessor_config.jsonConfiguration788 B —
special_tokens_map.jsonConfiguration614 B —
video_preprocessor_config.jsonConfiguration817 B —
README.mdDocumentation3.3 KB —
chat_template.jinjaOther5.3 KB —
.gitattributesRepository1.6 KB —
merges.txtTokenizer1.7 MB —
tokenizer.jsonTokenizer11.4 MB c0815702d207
tokenizer_config.jsonTokenizer11.0 KB —
vocab.jsonTokenizer2.8 MB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
14.8 GB
Download from Isaac Godfried

Released by Isaac Godfried through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published14.8 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About qwen-vl-8b-cairo-genizah-v18a

Can I use qwen-vl-8b-cairo-genizah-v18a commercially?

Yes. qwen-vl-8b-cairo-genizah-v18a 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 qwen-vl-8b-cairo-genizah-v18a's context length?

262,144 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Non-uniform GGUF quantizations of a 512-expert MoE, produced with GSQ and RCO, with a vision projector for multimodal use. This repository provides GGUF quantizations of Qwen3.8-Flash-Next at four sizes, together with the model's vision projector (mmproj) for multimodal use. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF and run unmodified in llama.cpp, Ollama, and LM Studio. A…

Open weights apache-2.0 gguf
View model

Model · Image and text to text

Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Michał Piszczek

I built this quant because the ready-made FP4 file answered the wrong question. It was fast, but on my short WikiText-2 control it scored 6.4949 PPL. Plain Q40 scored 6.3798. The first higher-quality hybrid went too far the other way: good perplexity, 34.19 tok/s, and no comfortable room for 256K plus vision. This is the build that survived both gates. It is a 17.1 GB, 5.01 BPW mixed-precision GGUF of Qwen/Qwen3.8-27B. It keeps large, tolerant matrices in native NVFP4 and spends more bits on selected attention, Gated DeltaNet, and late FFN tensors. The trained MTP layer remains embedded in the same GGUF. This is not a fine-tune. I built the private calibration workload from 5,472 messages…

Open weights apache-2.0
View model

Model · Image and text to text

Qwen3.8-27B-GGUF

GGML Org

Run with https://llama.app - https://huggingface.co/Qwen/Qwen3.8-27B - https://huggingface.co/incoai/Qwen3.8-27B-DFlash2 - add info

Open weights apache-2.0
View model

Model · Image and text to text

Huihui-Qwen3.8-27B-abliterated-GGUF

Huihui.ai

This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The newly added Huihui-Qwen3.8-27B-abliterated-Underdog-Saluki series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF. Only layers 22 to 52 (0-based indexing) have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF…

Open weights apache-2.0 transformers
View model

Qwen3.8-27B uncensored by HauhauCS 0/465 Refusals. This is the Aggressive variant: direct answers, no refusal behavior, and minimal preamble on hard prompts. Every text GGUF preserves Qwen3.8's native NextN head, and this release adds HauhauCS FastMTP: a specific acceleration sidecar qualified across the complete quant lineup at maximum native context. Vision is included through the separate BF16 projector. No changes to datasets or intended capabilities. This release preserves Qwen3.8-27B's text, reasoning, agentic, image, and video capabilities while applying the HauhauCS Aggressive uncensoring profile. Pick Aggressive when you specifically want the model to get to the answer without…

Open weights apache-2.0
View model

and it does so in 4bit and 8bit. Regular and MTP (fast) NEO IMATRIX GGUFs provided. (this model is part of the Qwen 3.6 27B Fable Fusion 711 pipelines: 2200+ likes, 3 million + downloads) instruct modes (2 new - Spoon / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model ctrl at the chat/message level). Model name has "plusIQ" in the name. A 12+12 (12 reasoning and 12 instruct) model with interactive optimization/help system will be releasing shortly too. BF16/16-bit MTP GGUF also avail. (there is also a extra robust "tools" version too - Q6 and Q8.) Extreme intelligence in a small package. Jaw dropping performance. Superior…

Open weights apache-2.0
View model