Downloads · 30 days
34
18% of all-time downloads
ralph-qwen3-8b-sub4-r3
tensor-tailor/ralph-qwen3-8b-sub4-r3
ralph-qwen3-8b-sub4-r3 is a machine learning model from tensor-tailor. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Sub4-tier GGUF compression of Qwen/Qwen3-8B — architecture and parameter count unchanged (8,190,735,360 weight-bearing parameters), weights re-stored at reduced bit-width. Submitted to the sub4 bit-tier on Bittensor s…
All-time downloads
193
Public
Repo size
4.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf4.6 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Sep 14, 2026
- SHA
- 1602e3d2
Base models
Model card
From the Hugging Face model README
ralph-qwen3-8b-sub4-r3
Sub4-tier GGUF compression of Qwen/Qwen3-8B — architecture and parameter count unchanged (8,190,735,360 weight-bearing parameters), weights re-stored at reduced bit-width. Submitted to the sub4 bit-tier on Bittensor subnet 40 (Ralph, model-compression).
License
Released under Apache License 2.0 — see LICENSE. This is a derivative of Qwen3-8B, itself
Apache-2.0; the original copyright/attribution notices and a description of what changed
(including the third-party quantization tooling used) are preserved in NOTICE.
Model overview
| Parent | Qwen/Qwen3-8B (Apache-2.0) |
| Parameters | 8,190,735,360 |
| Architecture | unchanged from parent |
| Format | GGUF |
| Bit tier | sub4 |
| File size | 4,614,304,832 bytes (~4.30 GiB) |
| Measured bits/weight | ~4.51 (file size / param count; embedding/output tensors kept at higher precision outside the compressed blocks) |
| Quantization method | llama.cpp, imatrix-calibrated |
No retraining or architectural modification — this is a post-training weight re-storage of the parent's own weights.
- License
- apache-2.0
- Created
- Aug 21, 2026
- Updated
- Sep 14, 2026