Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
anthracite-org/magnum-v4-27b - GGUF
This repo contains GGUF format model files for anthracite-org/magnum-v4-27b.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
magnum-v4-27b-Q2_K.gguf | Q2_K | 10.450 GB | smallest, significant quality loss - not recommended for most purposes |
magnum-v4-27b-Q3_K_S.gguf | Q3_K_S | 12.169 GB | very small, high quality loss |
magnum-v4-27b-Q3_K_M.gguf | Q3_K_M | 13.425 GB | very small, high quality loss |
magnum-v4-27b-Q3_K_L.gguf | Q3_K_L | 14.519 GB | small, substantial quality loss |
magnum-v4-27b-Q4_0.gguf | Q4_0 | 15.628 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
magnum-v4-27b-Q4_K_S.gguf | Q4_K_S | 15.739 GB | small, greater quality loss |
magnum-v4-27b-Q4_K_M.gguf | Q4_K_M | 16.645 GB | medium, balanced quality - recommended |
magnum-v4-27b-Q5_0.gguf | Q5_0 | 18.884 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
magnum-v4-27b-Q5_K_S.gguf | Q5_K_S | 18.884 GB | large, low quality loss - recommended |
magnum-v4-27b-Q5_K_M.gguf | Q5_K_M | 19.408 GB | large, very low quality loss - recommended |
magnum-v4-27b-Q6_K.gguf | Q6_K | 22.344 GB | very large, extremely low quality loss |
magnum-v4-27b-Q8_0.gguf | Q8_0 | 28.937 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/magnum-v4-27b-GGUF --include "magnum-v4-27b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf
), you can try:
huggingface-cli download tensorblock/magnum-v4-27b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 204
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for tensorblock/magnum-v4-27b-GGUF
Base model
anthracite-org/magnum-v4-27bDatasets used to train tensorblock/magnum-v4-27b-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard34.540
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard40.960
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard16.160
- acc_norm on GPQA (0-shot)Open LLM Leaderboard16.000
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.820
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard37.510