Gemma4-E2B-Dflash2-Android / benchmark.json
RoundRobin237's picture
Publish Gemma E2B BF16, Q4 GGUF and RaInfer NPU DFlash2 assets
77e134b verified
Raw History Blame Contribute Delete
14.8 kB
{
"date": "2026-10-15",
"metric": "Application completion_tokens / generation duration; prefill and model loading excluded",
"native_metric_difference": "Native committed_tokens excludes the initial prefill-produced token; do not equate raw native decode_tokens_per_second with the app counter",
"reference_java": {
"session": "adreno-improve-20261015-final",
"sample_index": 0,
"question": "final-java-product",
"prompt": "Java์—์„œ ๋‘ ์ •์ˆ˜๋ฅผ ๊ณฑํ•ด ๋ฐ˜ํ™˜ํ•˜๋Š” static ๋ฉ”์„œ๋“œ์™€ main์—์„œ 3๊ณผ 4๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅํ•˜๋Š” ์•„์ฃผ ์งง์€ ์‹คํ–‰ ๊ฐ€๋Šฅํ•œ ์˜ˆ์ œ๋ฅผ ์ฝ”๋“œ ๋ธ”๋ก ํ•˜๋‚˜๋กœ ์จ์ค˜.",
"ngram": false,
"usage": {
"prompt_tokens": 70,
"completion_tokens": 72,
"total_tokens": 142
},
"timings": {
"predicted_ms": 3770.3646860000003,
"predicted_per_second": 19.096295980955936,
"prompt_ms": 2244.620259
},
"wall_seconds": 6.090851664,
"accepted": 42,
"proposed": 90,
"rounds": 30,
"acceptance_fraction": 0.4666666666666667,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
"historical_sessions": [
{
"session": "adreno-improve-20261015-final",
"sample_index": 0,
"question": "final-java-product",
"prompt": "Java์—์„œ ๋‘ ์ •์ˆ˜๋ฅผ ๊ณฑํ•ด ๋ฐ˜ํ™˜ํ•˜๋Š” static ๋ฉ”์„œ๋“œ์™€ main์—์„œ 3๊ณผ 4๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅํ•˜๋Š” ์•„์ฃผ ์งง์€ ์‹คํ–‰ ๊ฐ€๋Šฅํ•œ ์˜ˆ์ œ๋ฅผ ์ฝ”๋“œ ๋ธ”๋ก ํ•˜๋‚˜๋กœ ์จ์ค˜.",
"ngram": false,
"usage": {
"prompt_tokens": 70,
"completion_tokens": 72,
"total_tokens": 142
},
"timings": {
"predicted_ms": 3770.3646860000003,
"predicted_per_second": 19.096295980955936,
"prompt_ms": 2244.620259
},
"wall_seconds": 6.090851664,
"accepted": 42,
"proposed": 90,
"rounds": 30,
"acceptance_fraction": 0.4666666666666667,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "adreno-improve-20261015-final",
"sample_index": 1,
"question": "final-meeting-change",
"prompt": "ํšŒ์‚ฌ ๋™๋ฃŒ์—๊ฒŒ ์˜ค๋Š˜ ์˜คํ›„ ํšŒ์˜๋ฅผ ๋‚ด์ผ ์˜ค์ „์œผ๋กœ ์˜ฎ๊ฒจ๋„ ๋˜๋Š”์ง€ ์ •์ค‘ํ•˜๊ฒŒ ๋ฌป๋Š” ์„ธ ๋ฌธ์žฅ ๋ฉ”์‹œ์ง€๋ฅผ ์จ์ค˜.",
"ngram": false,
"usage": {
"prompt_tokens": 62,
"completion_tokens": 52,
"total_tokens": 114
},
"timings": {
"predicted_ms": 4844.112967,
"predicted_per_second": 10.73467946644606,
"prompt_ms": 1921.057656
},
"wall_seconds": 6.823029737,
"accepted": 14,
"proposed": 114,
"rounds": 38,
"acceptance_fraction": 0.12280701754385964,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "adreno-improve-20261015-final",
"sample_index": 2,
"question": "english-meeting-new",
"prompt": null,
"ngram": false,
"usage": {
"prompt_tokens": 51,
"completion_tokens": 49,
"total_tokens": 100
},
"timings": {
"predicted_ms": 5632.5388,
"predicted_per_second": 8.69945183511208,
"prompt_ms": 1547.594687
},
"wall_seconds": 7.246587914,
"accepted": 3,
"proposed": 138,
"rounds": 46,
"acceptance_fraction": 0.021739130434782608,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "adreno-improve-20261015-final",
"sample_index": 3,
"question": "final-java-product",
"prompt": "Java์—์„œ ๋‘ ์ •์ˆ˜๋ฅผ ๊ณฑํ•ด ๋ฐ˜ํ™˜ํ•˜๋Š” static ๋ฉ”์„œ๋“œ์™€ main์—์„œ 3๊ณผ 4๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅํ•˜๋Š” ์•„์ฃผ ์งง์€ ์‹คํ–‰ ๊ฐ€๋Šฅํ•œ ์˜ˆ์ œ๋ฅผ ์ฝ”๋“œ ๋ธ”๋ก ํ•˜๋‚˜๋กœ ์จ์ค˜.",
"ngram": true,
"usage": {
"prompt_tokens": 70,
"completion_tokens": 72,
"total_tokens": 142
},
"timings": {
"predicted_ms": 3611.214269,
"predicted_per_second": 19.93789197668902,
"prompt_ms": 2076.6390619999997
},
"wall_seconds": 5.797856925,
"accepted": 42,
"proposed": 90,
"rounds": 30,
"acceptance_fraction": 0.4666666666666667,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "adreno-improve-20261015-final",
"sample_index": 4,
"question": "final-meeting-change",
"prompt": "ํšŒ์‚ฌ ๋™๋ฃŒ์—๊ฒŒ ์˜ค๋Š˜ ์˜คํ›„ ํšŒ์˜๋ฅผ ๋‚ด์ผ ์˜ค์ „์œผ๋กœ ์˜ฎ๊ฒจ๋„ ๋˜๋Š”์ง€ ์ •์ค‘ํ•˜๊ฒŒ ๋ฌป๋Š” ์„ธ ๋ฌธ์žฅ ๋ฉ”์‹œ์ง€๋ฅผ ์จ์ค˜.",
"ngram": true,
"usage": {
"prompt_tokens": 62,
"completion_tokens": 52,
"total_tokens": 114
},
"timings": {
"predicted_ms": 4569.645675000001,
"predicted_per_second": 11.379438078642716,
"prompt_ms": 1845.276822
},
"wall_seconds": 6.508259842,
"accepted": 14,
"proposed": 114,
"rounds": 38,
"acceptance_fraction": 0.12280701754385964,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "adreno-improve-20261015-final",
"sample_index": 5,
"question": "english-meeting-new",
"prompt": null,
"ngram": true,
"usage": {
"prompt_tokens": 51,
"completion_tokens": 49,
"total_tokens": 100
},
"timings": {
"predicted_ms": 5298.070154999999,
"predicted_per_second": 9.248650653249042,
"prompt_ms": 1502.878905
},
"wall_seconds": 6.827840831,
"accepted": 5,
"proposed": 132,
"rounds": 44,
"acceptance_fraction": 0.03787878787878788,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 1,
"ngram_accepted": 2,
"ngram_proposed": 3
},
{
"session": "adreno-improve-20261015-final",
"sample_index": 6,
"question": "final-java-product",
"prompt": "Java์—์„œ ๋‘ ์ •์ˆ˜๋ฅผ ๊ณฑํ•ด ๋ฐ˜ํ™˜ํ•˜๋Š” static ๋ฉ”์„œ๋“œ์™€ main์—์„œ 3๊ณผ 4๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅํ•˜๋Š” ์•„์ฃผ ์งง์€ ์‹คํ–‰ ๊ฐ€๋Šฅํ•œ ์˜ˆ์ œ๋ฅผ ์ฝ”๋“œ ๋ธ”๋ก ํ•˜๋‚˜๋กœ ์จ์ค˜.",
"ngram": false,
"usage": {
"prompt_tokens": 70,
"completion_tokens": 72,
"total_tokens": 142
},
"timings": {
"predicted_ms": 3665.962967,
"predicted_per_second": 19.640132933181373,
"prompt_ms": 2150.348073
},
"wall_seconds": 5.898703279,
"accepted": 42,
"proposed": 90,
"rounds": 30,
"acceptance_fraction": 0.4666666666666667,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "hybrid-release-20261015",
"sample_index": 0,
"question": "final-java-product",
"prompt": "Java์—์„œ ๋‘ ์ •์ˆ˜๋ฅผ ๊ณฑํ•ด ๋ฐ˜ํ™˜ํ•˜๋Š” static ๋ฉ”์„œ๋“œ์™€ main์—์„œ 3๊ณผ 4๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅํ•˜๋Š” ์•„์ฃผ ์งง์€ ์‹คํ–‰ ๊ฐ€๋Šฅํ•œ ์˜ˆ์ œ๋ฅผ ์ฝ”๋“œ ๋ธ”๋ก ํ•˜๋‚˜๋กœ ์จ์ค˜.",
"ngram": false,
"usage": {
"prompt_tokens": 70,
"completion_tokens": 72,
"total_tokens": 142
},
"timings": {
"predicted_ms": 4592.147551,
"predicted_per_second": 15.678938710129438,
"prompt_ms": 2590.2195300000003
},
"wall_seconds": 7.268555571,
"accepted": 42,
"proposed": 90,
"rounds": 30,
"acceptance_fraction": 0.4666666666666667,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "hybrid-release-20261015",
"sample_index": 1,
"question": "final-meeting-change",
"prompt": "ํšŒ์‚ฌ ๋™๋ฃŒ์—๊ฒŒ ์˜ค๋Š˜ ์˜คํ›„ ํšŒ์˜๋ฅผ ๋‚ด์ผ ์˜ค์ „์œผ๋กœ ์˜ฎ๊ฒจ๋„ ๋˜๋Š”์ง€ ์ •์ค‘ํ•˜๊ฒŒ ๋ฌป๋Š” ์„ธ ๋ฌธ์žฅ ๋ฉ”์‹œ์ง€๋ฅผ ์จ์ค˜.",
"ngram": false,
"usage": {
"prompt_tokens": 62,
"completion_tokens": 52,
"total_tokens": 114
},
"timings": {
"predicted_ms": 6094.054113,
"predicted_per_second": 8.532907492414976,
"prompt_ms": 2336.403801
},
"wall_seconds": 8.450074788,
"accepted": 14,
"proposed": 114,
"rounds": 38,
"acceptance_fraction": 0.12280701754385964,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "hybrid-release-20261015",
"sample_index": 2,
"question": "english-meeting-new",
"prompt": null,
"ngram": false,
"usage": {
"prompt_tokens": 51,
"completion_tokens": 49,
"total_tokens": 100
},
"timings": {
"predicted_ms": 7234.784268,
"predicted_per_second": 6.772834985105322,
"prompt_ms": 1919.921145
},
"wall_seconds": 9.202370309,
"accepted": 3,
"proposed": 138,
"rounds": 46,
"acceptance_fraction": 0.021739130434782608,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "hybrid-release-20261015",
"sample_index": 3,
"question": "final-java-product",
"prompt": "Java์—์„œ ๋‘ ์ •์ˆ˜๋ฅผ ๊ณฑํ•ด ๋ฐ˜ํ™˜ํ•˜๋Š” static ๋ฉ”์„œ๋“œ์™€ main์—์„œ 3๊ณผ 4๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅํ•˜๋Š” ์•„์ฃผ ์งง์€ ์‹คํ–‰ ๊ฐ€๋Šฅํ•œ ์˜ˆ์ œ๋ฅผ ์ฝ”๋“œ ๋ธ”๋ก ํ•˜๋‚˜๋กœ ์จ์ค˜.",
"ngram": true,
"usage": {
"prompt_tokens": 70,
"completion_tokens": 72,
"total_tokens": 142
},
"timings": {
"predicted_ms": 4571.105675,
"predicted_per_second": 15.751112557685511,
"prompt_ms": 2594.714114
},
"wall_seconds": 7.289967601,
"accepted": 42,
"proposed": 90,
"rounds": 30,
"acceptance_fraction": 0.4666666666666667,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "hybrid-release-20261015",
"sample_index": 4,
"question": "final-meeting-change",
"prompt": "ํšŒ์‚ฌ ๋™๋ฃŒ์—๊ฒŒ ์˜ค๋Š˜ ์˜คํ›„ ํšŒ์˜๋ฅผ ๋‚ด์ผ ์˜ค์ „์œผ๋กœ ์˜ฎ๊ฒจ๋„ ๋˜๋Š”์ง€ ์ •์ค‘ํ•˜๊ฒŒ ๋ฌป๋Š” ์„ธ ๋ฌธ์žฅ ๋ฉ”์‹œ์ง€๋ฅผ ์จ์ค˜.",
"ngram": true,
"usage": {
"prompt_tokens": 62,
"completion_tokens": 52,
"total_tokens": 114
},
"timings": {
"predicted_ms": 5879.252758,
"predicted_per_second": 8.844661411986873,
"prompt_ms": 2288.762395
},
"wall_seconds": 8.206408018,
"accepted": 14,
"proposed": 114,
"rounds": 38,
"acceptance_fraction": 0.12280701754385964,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
},
{
"session": "hybrid-release-20261015",
"sample_index": 5,
"question": "english-meeting-new",
"prompt": null,
"ngram": true,
"usage": {
"prompt_tokens": 51,
"completion_tokens": 49,
"total_tokens": 100
},
"timings": {
"predicted_ms": 6819.388331,
"predicted_per_second": 7.18539517353085,
"prompt_ms": 1889.928436
},
"wall_seconds": 8.785540934,
"accepted": 5,
"proposed": 132,
"rounds": 44,
"acceptance_fraction": 0.03787878787878788,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 1,
"ngram_accepted": 2,
"ngram_proposed": 3
},
{
"session": "hybrid-release-20261015",
"sample_index": 6,
"question": "final-java-product",
"prompt": "Java์—์„œ ๋‘ ์ •์ˆ˜๋ฅผ ๊ณฑํ•ด ๋ฐ˜ํ™˜ํ•˜๋Š” static ๋ฉ”์„œ๋“œ์™€ main์—์„œ 3๊ณผ 4๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅํ•˜๋Š” ์•„์ฃผ ์งง์€ ์‹คํ–‰ ๊ฐ€๋Šฅํ•œ ์˜ˆ์ œ๋ฅผ ์ฝ”๋“œ ๋ธ”๋ก ํ•˜๋‚˜๋กœ ์จ์ค˜.",
"ngram": false,
"usage": {
"prompt_tokens": 70,
"completion_tokens": 72,
"total_tokens": 142
},
"timings": {
"predicted_ms": 4710.549217,
"predicted_per_second": 15.284841890656336,
"prompt_ms": 2670.206092
},
"wall_seconds": 7.452902341,
"accepted": 42,
"proposed": 90,
"rounds": 30,
"acceptance_fraction": 0.4666666666666667,
"draft_backend": "cpu-cached-context-fp32-int8-head",
"actual_hexagon_execution": true,
"ngram_rounds": 0,
"ngram_accepted": 0,
"ngram_proposed": 0
}
],
"sample_max_tps": 19.93789197668902,
"not_a_cross_prompt_or_sustained_guarantee": true,
"recommended_settings": {
"context": 2048,
"target_verify_rows": 4,
"draft_candidates": 3,
"sampling": "greedy / temperature=0",
"cpu_workers": 4,
"body_workers": 1,
"gpu_head": false,
"fast_argmax": true,
"compact_logits": true,
"ngram": true,
"burst": false,
"fixed_affinity": false,
"profile": false
},
"historical_vs_public_source": "Device records predate public source packaging; same reference model assets, but wrapper/build/settings and thermal conditions varied. Not a fresh benchmark of the public commit.",
"quality_scope": "Limited identical-input token regression comparisons and PC javac execution for small Java examples; no broad quality equivalence claim",
"target_25_to_30_tps_achieved": false
}