Image-Text-to-Text
NInfer
qwen3.8
flash-next
nvfp4
fp8
int4
mixed-precision
blackwell
rtx-pro-6000
windows
single-gpu
multimodal
speculative-decoding
Instructions to use igorls/Qwen3.8-Flash-Next-mixed-NInfer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NInfer
How to use igorls/Qwen3.8-Flash-Next-mixed-NInfer with NInfer:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
docs: finalize mixed Flash-Next engineering preview
Browse files- README.md +2 -1
- artifact-manifest.json +2 -1
README.md
CHANGED
|
@@ -51,6 +51,7 @@ vLLM, llama.cpp, or Ollama. There is no Hugging Face hosted inference integratio
|
|
| 51 |
| Container | NInfer v2 |
|
| 52 |
| Model identity | `qwen3.8-flash-next` |
|
| 53 |
| Weight identity | `mixed-nvfp4-fp8-ple-int4` |
|
|
|
|
| 54 |
| Compatible engine revision | [`c81c88f6d66652be4607fb775333a6c63132f3f5`](https://github.com/igorls/ninfer/tree/c81c88f6d66652be4607fb775333a6c63132f3f5) |
|
| 55 |
|
| 56 |
Using the Hugging Face CLI:
|
|
@@ -59,7 +60,7 @@ Using the Hugging Face CLI:
|
|
| 59 |
hf download igorls/Qwen3.8-Flash-Next-mixed-NInfer `
|
| 60 |
qwen3_8_flash_next_mixed.ninfer artifact-manifest.json SHA256SUMS `
|
| 61 |
LICENSE NOTICE.md LICENSE-APACHE-2.0.txt README.md `
|
| 62 |
-
--local-dir .\models\flash-next
|
| 63 |
|
| 64 |
(Get-FileHash .\models\flash-next\qwen3_8_flash_next_mixed.ninfer -Algorithm SHA256).Hash
|
| 65 |
```
|
|
|
|
| 51 |
| Container | NInfer v2 |
|
| 52 |
| Model identity | `qwen3.8-flash-next` |
|
| 53 |
| Weight identity | `mixed-nvfp4-fp8-ple-int4` |
|
| 54 |
+
| Release revision | `preview-2026-09-07` |
|
| 55 |
| Compatible engine revision | [`c81c88f6d66652be4607fb775333a6c63132f3f5`](https://github.com/igorls/ninfer/tree/c81c88f6d66652be4607fb775333a6c63132f3f5) |
|
| 56 |
|
| 57 |
Using the Hugging Face CLI:
|
|
|
|
| 60 |
hf download igorls/Qwen3.8-Flash-Next-mixed-NInfer `
|
| 61 |
qwen3_8_flash_next_mixed.ninfer artifact-manifest.json SHA256SUMS `
|
| 62 |
LICENSE NOTICE.md LICENSE-APACHE-2.0.txt README.md `
|
| 63 |
+
--revision preview-2026-09-07 --local-dir .\models\flash-next
|
| 64 |
|
| 65 |
(Get-FileHash .\models\flash-next\qwen3_8_flash_next_mixed.ninfer -Algorithm SHA256).Hash
|
| 66 |
```
|
artifact-manifest.json
CHANGED
|
@@ -2,7 +2,8 @@
|
|
| 2 |
"schema": "ninfer.artifact-manifest",
|
| 3 |
"schema_version": 1,
|
| 4 |
"release": {
|
| 5 |
-
"status": "early-access-engineering-preview",
|
|
|
|
| 6 |
"prepared_date": "2026-09-07",
|
| 7 |
"repo_id": "igorls/Qwen3.8-Flash-Next-mixed-NInfer"
|
| 8 |
},
|
|
|
|
| 2 |
"schema": "ninfer.artifact-manifest",
|
| 3 |
"schema_version": 1,
|
| 4 |
"release": {
|
| 5 |
+
"status": "early-access-engineering-preview",
|
| 6 |
+
"tag": "preview-2026-09-07",
|
| 7 |
"prepared_date": "2026-09-07",
|
| 8 |
"repo_id": "igorls/Qwen3.8-Flash-Next-mixed-NInfer"
|
| 9 |
},
|