Any-to-Any
MLX
Safetensors
gemma4
mlx-vlm
rlcd
multimodal
classification
parallel-inference
image-text-to-text
audio
video
4-bit precision
Instructions to use larkooo/gemma-e2b-rlcd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use larkooo/gemma-e2b-rlcd with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download larkooo/gemma-e2b-rlcd --local-dir gemma-e2b-rlcd
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download reports/cache-gathered.json from larkooo/gemma-e2b-rlcd: direct link, hf CLI and curl.
- Browser
- Download file 7.34 kB
-
https://huggingface.co/larkooo/gemma-e2b-rlcd/resolve/main/reports/cache-gathered.json
- Command line
-
hf download hf://larkooo/gemma-e2b-rlcd/reports/cache-gathered.json
-
curl -L -o cache-gathered.json https://huggingface.co/larkooo/gemma-e2b-rlcd/resolve/main/reports/cache-gathered.json
7.34 kB
| { | |
| "model": "models/gemma-4-e2b-it-4bit", | |
| "compute_dtype": "float32", | |
| "status": "cache_numerics_and_timing_probe_not_quality_benchmark", | |
| "results": [ | |
| { | |
| "state": "text", | |
| "prefix_tokens": 50, | |
| "suffix_lengths": [ | |
| 111, | |
| 99, | |
| 111, | |
| 111 | |
| ], | |
| "cached_serial_vs_uncached": { | |
| "max_logit_delta": 0.032517433166503906, | |
| "max_probability_delta": 4.89707640993764e-07, | |
| "all_winners_match": true | |
| }, | |
| "cached_batch_vs_uncached": { | |
| "max_logit_delta": 0.047650814056396484, | |
| "max_probability_delta": 9.921427801540261e-07, | |
| "all_winners_match": true | |
| }, | |
| "reversed_batch_vs_original": { | |
| "max_logit_delta": 0.0, | |
| "max_probability_delta": 0.0, | |
| "all_winners_match": true | |
| }, | |
| "prefix_unchanged": true, | |
| "branch_batch_sizes": [ | |
| 4 | |
| ], | |
| "warm_seconds": { | |
| "uncached": [ | |
| 0.24687987499055453, | |
| 0.24587425001664087, | |
| 0.24255950000951998 | |
| ], | |
| "cached_batched": [ | |
| 0.17461620797985233, | |
| 0.18541070900391787, | |
| 0.16993425000691786 | |
| ] | |
| }, | |
| "warm_median_seconds": { | |
| "uncached": 0.24587425001664087, | |
| "cached_batched": 0.17461620797985233 | |
| }, | |
| "speedup": 1.4080837790556675 | |
| }, | |
| { | |
| "state": "image", | |
| "prefix_tokens": 295, | |
| "suffix_lengths": [ | |
| 111, | |
| 99, | |
| 111, | |
| 111 | |
| ], | |
| "cached_serial_vs_uncached": { | |
| "max_logit_delta": 0.04843616485595703, | |
| "max_probability_delta": 0.0007440930557797154, | |
| "all_winners_match": true | |
| }, | |
| "cached_batch_vs_uncached": { | |
| "max_logit_delta": 0.02086162567138672, | |
| "max_probability_delta": 0.0013810108588161452, | |
| "all_winners_match": true | |
| }, | |
| "reversed_batch_vs_original": { | |
| "max_logit_delta": 0.0, | |
| "max_probability_delta": 0.0, | |
| "all_winners_match": true | |
| }, | |
| "prefix_unchanged": true, | |
| "branch_batch_sizes": [ | |
| 4 | |
| ], | |
| "warm_seconds": { | |
| "uncached": [ | |
| 2.039599666983122, | |
| 1.9174777079897467, | |
| 1.8907254159857985 | |
| ], | |
| "cached_batched": [ | |
| 0.5769222080125473, | |
| 0.5648717090080027, | |
| 0.5669595829967875 | |
| ] | |
| }, | |
| "warm_median_seconds": { | |
| "uncached": 1.9174777079897467, | |
| "cached_batched": 0.5669595829967875 | |
| }, | |
| "speedup": 3.3820359783928575 | |
| }, | |
| { | |
| "state": "speech", | |
| "prefix_tokens": 86, | |
| "suffix_lengths": [ | |
| 111, | |
| 99, | |
| 111, | |
| 111 | |
| ], | |
| "cached_serial_vs_uncached": { | |
| "max_logit_delta": 0.08770561218261719, | |
| "max_probability_delta": 0.013604034682185018, | |
| "all_winners_match": true | |
| }, | |
| "cached_batch_vs_uncached": { | |
| "max_logit_delta": 0.051482200622558594, | |
| "max_probability_delta": 0.008151936419399375, | |
| "all_winners_match": true | |
| }, | |
| "reversed_batch_vs_original": { | |
| "max_logit_delta": 0.0, | |
| "max_probability_delta": 0.0, | |
| "all_winners_match": true | |
| }, | |
| "prefix_unchanged": true, | |
| "branch_batch_sizes": [ | |
| 4 | |
| ], | |
| "warm_seconds": { | |
| "uncached": [ | |
| 0.33885545798693784, | |
| 0.34261837499798276, | |
| 0.33428337500663474 | |
| ], | |
| "cached_batched": [ | |
| 0.199704833998112, | |
| 0.19404779098113067, | |
| 0.18803491699509323 | |
| ] | |
| }, | |
| "warm_median_seconds": { | |
| "uncached": 0.33885545798693784, | |
| "cached_batched": 0.19404779098113067 | |
| }, | |
| "speedup": 1.7462474387038416 | |
| }, | |
| { | |
| "state": "video", | |
| "prefix_tokens": 328, | |
| "suffix_lengths": [ | |
| 111, | |
| 99, | |
| 111, | |
| 111 | |
| ], | |
| "cached_serial_vs_uncached": { | |
| "max_logit_delta": 0.007994651794433594, | |
| "max_probability_delta": 0.00047290616548957554, | |
| "all_winners_match": true | |
| }, | |
| "cached_batch_vs_uncached": { | |
| "max_logit_delta": 0.016923904418945312, | |
| "max_probability_delta": 0.0007754361118514908, | |
| "all_winners_match": true | |
| }, | |
| "reversed_batch_vs_original": { | |
| "max_logit_delta": 0.0, | |
| "max_probability_delta": 0.0, | |
| "all_winners_match": true | |
| }, | |
| "prefix_unchanged": true, | |
| "branch_batch_sizes": [ | |
| 4 | |
| ], | |
| "warm_seconds": { | |
| "uncached": [ | |
| 1.87490254198201, | |
| 1.9036407500097994, | |
| 2.002558832988143 | |
| ], | |
| "cached_batched": [ | |
| 0.6002716670045629, | |
| 0.5745167080021929, | |
| 0.6253891669912264 | |
| ] | |
| }, | |
| "warm_median_seconds": { | |
| "uncached": 1.9036407500097994, | |
| "cached_batched": 0.6002716670045629 | |
| }, | |
| "speedup": 3.1712986879910976 | |
| }, | |
| { | |
| "state": "video_speech", | |
| "prefix_tokens": 431, | |
| "suffix_lengths": [ | |
| 111, | |
| 99, | |
| 111, | |
| 111 | |
| ], | |
| "cached_serial_vs_uncached": { | |
| "max_logit_delta": 0.05509662628173828, | |
| "max_probability_delta": 0.005538062741424418, | |
| "all_winners_match": true | |
| }, | |
| "cached_batch_vs_uncached": { | |
| "max_logit_delta": 0.03372955322265625, | |
| "max_probability_delta": 0.002709010563853226, | |
| "all_winners_match": true | |
| }, | |
| "reversed_batch_vs_original": { | |
| "max_logit_delta": 0.0, | |
| "max_probability_delta": 0.0, | |
| "all_winners_match": true | |
| }, | |
| "prefix_unchanged": true, | |
| "branch_batch_sizes": [ | |
| 4 | |
| ], | |
| "warm_seconds": { | |
| "uncached": [ | |
| 2.368914416991174, | |
| 2.1928319169965107, | |
| 2.2464634170173667 | |
| ], | |
| "cached_batched": [ | |
| 0.7086897499975748, | |
| 0.6427362920076121, | |
| 0.8200017909985036 | |
| ] | |
| }, | |
| "warm_median_seconds": { | |
| "uncached": 2.2464634170173667, | |
| "cached_batched": 0.7086897499975748 | |
| }, | |
| "speedup": 3.169882754795105 | |
| }, | |
| { | |
| "state": "long_text", | |
| "prefix_tokens": 1250, | |
| "suffix_lengths": [ | |
| 111, | |
| 99, | |
| 111, | |
| 111 | |
| ], | |
| "cached_serial_vs_uncached": { | |
| "max_logit_delta": 0.028132915496826172, | |
| "max_probability_delta": 1.1824594636777874e-09, | |
| "all_winners_match": true | |
| }, | |
| "cached_batch_vs_uncached": { | |
| "max_logit_delta": 0.041655540466308594, | |
| "max_probability_delta": 2.3831407958141426e-09, | |
| "all_winners_match": true | |
| }, | |
| "reversed_batch_vs_original": { | |
| "max_logit_delta": 0.0, | |
| "max_probability_delta": 0.0, | |
| "all_winners_match": true | |
| }, | |
| "prefix_unchanged": true, | |
| "branch_batch_sizes": [ | |
| 4 | |
| ], | |
| "warm_seconds": { | |
| "uncached": [ | |
| 1.887113375007175, | |
| 1.7507582920079585, | |
| 1.7365583749779034 | |
| ], | |
| "cached_batched": [ | |
| 0.5613800830033142, | |
| 0.5454969170095865, | |
| 0.5390715000103228 | |
| ] | |
| }, | |
| "warm_median_seconds": { | |
| "uncached": 1.7507582920079585, | |
| "cached_batched": 0.5454969170095865 | |
| }, | |
| "speedup": 3.2094742195897523 | |
| } | |
| ] | |
| } | |