Downloads · 30 days
35
21% of all-time downloads
granite41-3b-german-tutor-v4-4bit
kessenma/granite41-3b-german-tutor-v4-4bit
granite41-3b-german-tutor-v4-4bit is a text generation model from kessenma. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
QLoRA fine-tune (r=32) of ibm-granite/granite-4.1-3b for German grammar tutoring, quantized to 4-bit (group size 64, affine) for on-device MLX inference. Sibling of granite33-2b-german-tutor-v4-4bit trained on the sam…
All-time downloads
163
Public
Parameters
3.4B
1.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.9 GB · 100%
Parameter types
How the weights are stored.
U323.4B · 100%
Base models
Model card
From the Hugging Face model README
Granite 4.1 3B German Tutor v4 (MLX 4-bit)
QLoRA fine-tune (r=32) of ibm-granite/granite-4.1-3b for German grammar tutoring, quantized to
4-bit (group size 64, affine) for on-device MLX inference. Sibling of
granite33-2b-german-tutor-v4-4bit
trained on the same corpus; this one trades ~0.4 GB more weight for markedly better error-catching.
Scores
App-guard convention (a reply counts only if the app's parser would show it to the learner).
| suite | items | granite-4.1 v4 | granite-3.3 v4 | stock 4.1 |
|---|---|---|---|---|
| core grammar (v0) | 60 | 47 (78%) | 46 (77%) | 31 (52%) |
| extension (v1ext) | 61 | 46 (75%) | 39 (64%) | 39 (64%) |
| holdout (v2) | 82 | 71 (87%) | 68 (83%) | 41 (50%) |
| combined | 203 | 164 (81%) | 153 (75%) | 111 (55%) |
Behavior: false-correction rate 9%, miss rate 25% (the 3.3 sibling: 0% / 43% — this model actually attempts corrections instead of defaulting to OK). Naturalness: modal particles 12.0 per 100 tokens, follow-up rate 0.82.
Paired vs the 3.3 sibling on identical items: 26 gained / 15 lost (exact McNemar p = 0.12).
Notes
- ~100k vocabulary tokenizes German at roughly half the tokens of the 3.3 sibling's 49k BPE, largely offsetting the larger parameter count in per-sentence latency.
- Trained on corpus v4: 42,841 rows, 15 grammar phenomena at 70% fix / 30% ok per phenomenon, teacher-generated (gemma-4-31B bulk + Claude Sonnet), LanguageTool + spaCy validated.
Output contract
OK for correct sentences, otherwise:
FIX: <corrected sentence>
WHY: <one-line explanation>
HINT: <question that nudges the learner>
- Task
- Text Generation
- Library
- mlx
- Type
- granite
- License
- apache-2.0
- Languages
- de, en
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026