Downloads · 30 days
0
Qwen3.8-27B-CoreAI-H8
drbh/Qwen3.8-27B-CoreAI-H8
Qwen3.8-27B-CoreAI-H8 is a text generation model from drbh. Use it when you need the model to write or continue text. It is set up for coreai. The card lists the license as apache-2.0.
Prebuilt Apple Core AI bundles for coreai-rs. The model body uses INT4 linear quantization and the output head uses INT8 quantization. Every bundle is the same weights; they differ only in the context bound compiled i…
Access
Public
Updated Sep 3, 2026
Repo size
88 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mlirb88 GB · 100%
At a glance
- Task
- Text Generation
- Library
- coreai
- License
- apache-2.0
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 47c3c8ee
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B Core AI H8
Prebuilt Apple Core AI bundles for
coreai-rs. The model body uses INT4
linear quantization and the output head uses INT8 quantization. Every bundle
is the same weights; they differ only in the context bound compiled into the
graph. The runtime allocates KV state on demand up to that bound, at 64 KiB
per token, so pick the largest bound whose full allocation fits your machine
next to the 17.6 GB model.
| Folder | Context bound (tokens) | KV state at full context |
|---|---|---|
| repo root | 4096 | 0.3 GB |
c8k/ | 8192 | 0.5 GB |
c32k/ | 32768 | 2.1 GB |
c64k/ | 65536 | 4.3 GB |
c128k/ | 131072 | 8.6 GB |
The bundles target Apple silicon with macOS 27 and Xcode 27. Download and run one through the repository's Qwen/Pi server:
make serve # c8k by default
make serve QWEN_CONTEXT=c32k MAX_CONTEXT_TOKENS=32768
Prefill runs near 85 tokens/s on an M3 Max, so a 32k-token prompt takes over six minutes before the first token.
Source model: Qwen/Qwen3.8-27B, revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0.
- Task
- Text Generation
- Library
- coreai
- License
- apache-2.0
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026