Downloads · 30 days
23
7% of all-time downloads
boweizh1204/qwen3-8b-ralph-sub4-c1b-20260910
qwen3-8b-ralph-sub4-c1b-20260910 is a machine learning model from boweizh1204. 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.
Compressed derivative of Qwen/Qwen3-8B submitted to the sub4 bit-tier of Bittensor subnet 40 (Ralph, model compression). Architecture and parameter count are unchanged from the parent; weights are re-stored at reduced…
Downloads · 30 days
23
7% of all-time downloads
All-time downloads
325
Public
Repo size
4.6 GB
Likes
0
Public
Click a slice to open those files.
.gguf4.6 GB · 100%
From the Hugging Face model README
Compressed derivative of Qwen/Qwen3-8B submitted to the sub4 bit-tier of Bittensor subnet 40 (Ralph, model compression). Architecture and parameter count are unchanged from the parent; weights are re-stored at reduced bit-width.
Released under the Apache License 2.0 — see LICENSE. This is a derivative of Qwen3-8B, itself Apache-2.0;
the parent's copyright and attribution notices, a description of what changed, the data used and the third-party
tooling involved are preserved in NOTICE. The exact artifact is model.gguf at revision 3c21306c630dac6440b37ad67b965a4b9b787cf9
(SHA-256 b2ec80dce90258bbe9555a67983dea595d91f35cae48ca0d54c714eae8100edf); adding this model card and license files does not alter that file.
| Parent | Qwen/Qwen3-8B (Apache-2.0) |
| Architecture | unchanged from parent |
| Format | GGUF (llama.cpp) |
| Bit tier | sub4 (gate: ≤4.0 code bits and ≤5.0 container bits per weight) |
| File size | 4,614,304,896 bytes |
| Measured bits/weight | 4.0 code bits, 4.5 container bits (validator-measured) |
| Method | Post-training weight re-storage of the parent's own weights: llama.cpp pure Q4_K quantization with an importance-matrix (imatrix) calibration computed on the bf16 parent at 2048-token context over an exam-proportional sample of public trajectory datasets. No retraining, distillation or architectural change. |
Upstream terms to preserve: Qwen3-8B's Apache-2.0 license and attribution (kept in NOTICE); llama.cpp's MIT license
for the GGUF tooling; the dataset licenses listed in NOTICE (Apache-2.0, MIT, CC-BY-4.0 — attribution only).