Downloads · 30 days
38
11% of all-time downloads
Chungulus/Agents-A1-Q3_K_M-imatrix-gguf-fable5-calibrated
Agents-A1-Q3_K_M-imatrix-gguf-fable5-calibrated is a machine learning model from Chungulus. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for llama.cpp. The card lists the license as apache-2.0.
Fable-5 trace calibrated imatrix GGUF quant of InternScience/Agents-A1.
Downloads · 30 days
38
11% of all-time downloads
All-time downloads
345
Public
Repo size
16.8 GB
Likes
2
Public
Click a slice to open those files.
.gguf16.8 GB · 100%
From the Hugging Face model README
Fable-5 trace calibrated imatrix GGUF quant of InternScience/Agents-A1.
| File | Size | SHA-256 |
|---|---|---|
Agents-A1-Q3_K_M-imatrix-gguf-fable5-calibrated.gguf | 15.61 GiB | ec40a523a23df7a4241875ec4c6039242617d46ad6395825f1d33361abf4a665 |
llama-cli -hf Chungulus/Agents-A1-Q3_K_M-imatrix-gguf-fable5-calibrated:Agents-A1-Q3_K_M-imatrix-gguf-fable5-calibrated.gguf -p "Write a Python sorting function" -n 160
ollama create agents-a1-q3_k_m-imatrix -f Modelfile
ollama run agents-a1-q3_k_m-imatrix
| Use case | Recommendation |
|---|---|
| Recommended hardware | 12-16 GB RAM |
| Best for | low-memory balance |
F16 baseline mini accuracy: 89.58%. F16 baseline PPL on KL holdout: 13.0194.
| Metric | Value |
|---|---|
| Mini accuracy | 89.58% |
| Retention vs F16 | 100.00% |
| Mean KLD vs F16 | 0.046980 |
| Same top p | 88.09% |
Glint-Research/Fable-5-tracese05c417852fc59fd8da758e68b352732423ca0cb