TokForge Bonsai Image 4B GGUF
Website: Discord: Google Play: iOS TestFlight:
Fonte do modelo
- Tipo
- VAE
- Tamanho do arquivo
- 160 MB
- Modelo base
- prism-ml/bonsai-image-ternary-4B-gemlite-2bit
- Versão
- vflux2-vae
- Atualizado
- 6 de out. de 2026
- Downloads
- 411
- Fonte
- Hugging Face
Descrição da fonte
TokForge
- Website: https://tokforge.ai
- Discord: https://discord.gg/Acv3CBtfVm
- Google Play: https://play.google.com/store/apps/details?id=dev.tokforge
- iOS TestFlight: https://testflight.apple.com/join/jnufjzRr
Runs on-device in the TokForge app.
TokForge-Bonsai-Image-4B-GGUF
TokForge-packaged Bonsai Image 4B / FLUX.2 Klein bundle for on-device Android image generation.
This repository contains the runtime files used by the TokForge Android image-generation route:
bonsai_klein_official_tq2g128.gguf— TokForge/sd.cpp GGUF conversion of the Bonsai Image 4B diffusion transformer.Qwen3-4B-Q4_K_M.gguf— Qwen3-4B text encoder in GGUF Q4_K_M format.flux2-vae.safetensors— FLUX.2 Klein VAE, renamed for TokForge bundle discovery.
Attribution: Bonsai Image is by Prism ML. FLUX.2 Klein is by Black Forest Labs, and the text encoder is based on Qwen3-4B by Qwen/Alibaba Cloud. This repository changes the deployment packaging and runtime formats only.
Recommended TokForge Route
This is a guarded beta image-generation bundle, not a universal default for every Android phone.
| Device class | Route | Status |
|---|---|---|
| 16-24 GB Qualcomm/Adreno | 512x512, OpenCL, 2 steps | Quality Beta / Lab |
| 12-16 GB Qualcomm/Adreno | 512x512, OpenCL, 2-3 steps | Quality Beta / Lab after device proof |
| CPU, Tensor, Exynos, Mali, Xclipse | sub-512 or CPU preview | Preview only |
| Q8/OpenCL experiments | varies | Demoted until native quality is fixed |
TokForge uses conservative labels:
- Quality Beta requires coherent 512x512 output, repeatability, and no flat/corrupt image.
- Preview is used for sub-512, CPU, low-memory, or visibly soft/warped outputs.
- Lab is used for OpenCL/server paths that require explicit opt-in.
Inference Settings
The Bonsai route expects the published low-guidance FLUX.2 Klein/Bonsai-style recipe:
| Setting | Value |
|---|---|
| Sampler | Euler |
| Scheduler | simple / FlowMatch-style |
| CFG scale | 1.0 |
| Distilled guidance | 1.0 |
| Flow shift | 3.0 |
| Default canvas | 512x512 |
| Default quality steps | 2 on certified Adreno OpenCL |
Higher step counts are not automatically better. TokForge currently treats 1-step output as too smeared for Quality Beta.
Files
| File | Size | SHA-256 |
|---|---|---|
bonsai_klein_official_tq2g128.gguf | 1.3 GB | 2a6da84102513a3a14a955edeb84ef0e347b51f9f13cc539c939ea78410a3eb7 |
Qwen3-4B-Q4_K_M.gguf | 2.4 GB | 7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5 |
flux2-vae.safetensors | 161 MB | ca70d2202afe6415bdbcb8793ba8cd99fd159cfe6192381504d6c4d3036e0f04 |
manifest.json | metadata | Runtime recipe and route policy |
Usage with TokForge
This bundle is intended for TokForge, a free Android app for private on-device AI.
- Open TokForge.
- Go to Models or Image Creation settings.
- Download Bonsai Image 4B (TokForge).
- Use natural chat phrasing such as
generate an image of a red car on a city street, or use the image-generation chip/button path.
TokForge will unload/reload the chat model when needed on memory-constrained devices.
Validation Snapshot
TokForge fleet validation on 2026-05-31 found:
- RedMagic high-memory Adreno: 512x512/2 OpenCL Quality Beta, around 80-81 seconds for the required prompt set.
- Lenovo 12-16 GB Adreno: 512x512/2 OpenCL Quality Beta, around 130 seconds with normal one-shot helper; faster warm-server lab mode exists but is not part of the normal APK.
- Tensor/Exynos/Mali/Xclipse and CPU routes remain Preview unless separately certified.
The sample contact sheet in samples/adreno_quality_beta_contact_sheet.png shows certified Adreno Quality Beta outputs for car, tree, restaurant, beach, house, and person prompts.
Limitations
- This is a runtime bundle, not a standard Diffusers training checkpoint.
- OpenCL acceleration is guarded and currently targeted at high-memory Qualcomm/Adreno devices.
- Non-Adreno GPU paths are not release-green.
- Low-memory CPU routes are Preview only.
- The output quality gate is visual/coherence-first; faster blurry or flat routes are demoted.
Attribution
This bundle is derived from:
- Prism ML Bonsai Image
- Prism ML Bonsai unpacked FP16 release
- Black Forest Labs FLUX.2 Klein 4B
- Qwen/Qwen3-4B
All credit for the model architecture, training, and source releases goes to the original authors. This repository packages converted/runtime files for TokForge mobile deployment.
Per the upstream notice: "Created using Bonsai Image by Prism ML."
Community
- Website: tokforge.ai
- GitHub: darkmaniac7/Elysium
Fontes
1 fonte
Fontes
1 fonteVerificado 6 de out.
Artefatos de modelo
1 artefato
Artefatos de modelo
1 artefatoTrechos de fonte
3 trechos
Trechos de fonte
3 trechos--- license: apache-2.0 language: - en pipeline_tag: text-to-image base_model: prism-ml/bonsai-image-ternary-4B-gemlite-2bit base_model_relation: quantized tags: - bonsai - flux - gguf - text-to-image - android - mobile - on-device - tokforge - opencl - sd.cpp --- ## TokForge - **Website:** https://tokforge.ai - **Discord:** https://discord.gg/Acv3CBtfVm - **Google Play:** https://play.google.com/store/apps/details?id=dev.tokforge - **iOS TestFlight:** https://testflight.apple.com/join/jnufjzRr Runs on-device in the TokForge app. # TokForge-Bonsai-Image-4B-GGUF TokForge-packaged Bonsai Image 4B / FLUX.2 Klein bundle for on-device Android image generation. This repository contains the runtime files used by the TokForge Android image-generation route: - `bonsai_klein_official_tq2g128.gguf` — TokForge/sd.cpp GGUF conversion of the Bonsai Image 4B diffusion transformer. - `Qwen3-4B-Q4_K_M.gguf` — Qwen3-4B text encoder in GGUF Q4_K_M format. - `flux2-vae.safetensors` — FLUX.2 Klein VAE, renamed for TokForge bundle discovery. > Attribution: Bonsai Image is by [Prism ML](https://huggingface.co/prism-ml). FLUX.2 Klein is by [Black Forest Labs](https://huggingface.co/black-forest-labs), and the text encoder is based on [Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) by Qwen/Alibaba Cloud. This repository changes the deployment packaging and runtime formats only. ## Recommended TokForge Route This is a guarded beta image-generation bundle, not a universal default for every Android phone. | Device class | Route | Status | |---|---|---| | 16-24 GB Qualcomm/Adreno | 512x512, OpenCL, 2 steps | Quality Beta / Lab | | 12-16 GB Qualcomm/Adreno | 512x512, OpenCL, 2-3 steps | Quality Beta / Lab after device proof | | CPU, Tensor, Exynos, Mali, Xclipse | sub-512 or CPU preview | Preview only | | Q8/OpenCL experiments | varies | Demoted until native quality is fixed | TokForge uses conservative labels: - **Quality Beta** requires coherent 512x512 output, repeatability, and no flat/corrupt image. - **Preview** is used for sub-512, CPU, low-memory, or visibly soft/warped outputs. - **Lab** is used for OpenCL/server paths that require explicit opt-in. ## Inference Settings The Bonsai route expects the published low-guidance FLUX.2 Klein/Bonsai-style recipe: | Setting | Value | |---|---| | Sampler | Euler | | Scheduler | simple / FlowMatch-style | | CF...
--- license: apache-2.0 language: - en pipeline_tag: text-to-image base_model: - prism-ml/bonsai-image-ternary-4B-gemlite-2bit - prism-ml/bonsai-image-ternary-4B-unpacked - black-forest-labs/FLUX.2-klein-4B - Qwen/Qwen3-4B tags: - bonsai - flux - gguf - text-to-image - android - mobile - on-device - tokforge - opencl - sd.cpp --- ## TokForge - **Website:** https://tokforge.ai - **Discord:** https://discord.gg/Acv3CBtfVm - **Google Play:** https://play.google.com/store/apps/details?id=dev.tokforge - **iOS TestFlight:** https://testflight.apple.com/join/jnufjzRr Runs on-device in the TokForge app. # TokForge-Bonsai-Image-4B-GGUF TokForge-packaged Bonsai Image 4B / FLUX.2 Klein bundle for on-device Android image generation. This repository contains the runtime files used by the TokForge Android image-generation route: - `bonsai_klein_official_tq2g128.gguf` — TokForge/sd.cpp GGUF conversion of the Bonsai Image 4B diffusion transformer. - `Qwen3-4B-Q4_K_M.gguf` — Qwen3-4B text encoder in GGUF Q4_K_M format. - `flux2-vae.safetensors` — FLUX.2 Klein VAE, renamed for TokForge bundle discovery. > Attribution: Bonsai Image is by [Prism ML](https://huggingface.co/prism-ml). FLUX.2 Klein is by [Black Forest Labs](https://huggingface.co/black-forest-labs), and the text encoder is based on [Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) by Qwen/Alibaba Cloud. This repository changes the deployment packaging and runtime formats only. ## Recommended TokForge Route This is a guarded beta image-generation bundle, not a universal default for every Android phone. | Device class | Route | Status | |---|---|---| | 16-24 GB Qualcomm/Adreno | 512x512, OpenCL, 2 steps | Quality Beta / Lab | | 12-16 GB Qualcomm/Adreno | 512x512, OpenCL, 2-3 steps | Quality Beta / Lab after device proof | | CPU, Tensor, Exynos, Mali, Xclipse | sub-512 or CPU preview | Preview only | | Q8/OpenCL experiments | varies | Demoted until native quality is fixed | TokForge uses conservative labels: - **Quality Beta** requires coherent 512x512 output, repeatability, and no flat/corrupt image. - **Preview** is used for sub-512, CPU, low-memory, or visibly soft/warped outputs. - **Lab** is used for OpenCL/server paths that require explicit opt-in. ## Inference Settings The Bonsai route expects the published low-guidance FLUX.2 Klein/Bonsai-style recipe: | Setting | Value | |---...
Source context: 411 downloads · 2 likes · Pipeline text-to-image · Repo darkmaniac7/TokForge-Bonsai-Image-4B-GGUF
