Spaces:
Running
Running
bench : update benches
Browse files- scripts/bench-all-gg.txt +100 -99
scripts/bench-all-gg.txt
CHANGED
|
@@ -111,62 +111,61 @@ make -j && ./scripts/bench-all.sh 1 1 0
|
|
| 111 |
|
| 112 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 113 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 114 |
-
| M2 ULTRA | METAL | tiny | 1 | 0 |
|
| 115 |
-
| M2 ULTRA | METAL | tiny-q5_0 | 1 | 0 | 10.
|
| 116 |
-
| M2 ULTRA | METAL | tiny-q5_1 | 1 | 0 |
|
| 117 |
-
| M2 ULTRA | METAL | tiny-q8_0 | 1 | 0 | 9.
|
| 118 |
-
| M2 ULTRA | METAL | base | 1 | 0 |
|
| 119 |
-
| M2 ULTRA | METAL | base-q5_0 | 1 | 0 | 16.
|
| 120 |
-
| M2 ULTRA | METAL | base-q5_1 | 1 | 0 | 16.
|
| 121 |
-
| M2 ULTRA | METAL | base-q8_0 | 1 | 0 | 16.
|
| 122 |
-
| M2 ULTRA | METAL | small | 1 | 0 | 45.
|
| 123 |
-
| M2 ULTRA | METAL | small-q5_0 | 1 | 0 | 50.
|
| 124 |
-
| M2 ULTRA | METAL | small-q5_1 | 1 | 0 | 50.
|
| 125 |
-
| M2 ULTRA | METAL | small-q8_0 | 1 | 0 | 47.
|
| 126 |
-
| M2 ULTRA | METAL | medium | 1 | 0 | 122.
|
| 127 |
-
| M2 ULTRA | METAL | medium-q5_0 | 1 | 0 | 140.
|
| 128 |
-
| M2 ULTRA | METAL | medium-q5_1 | 1 | 0 | 140.
|
| 129 |
-
| M2 ULTRA | METAL | medium-q8_0 | 1 | 0 | 131.
|
| 130 |
-
| M2 ULTRA | METAL | medium-dis | 1 | 0 | 110.
|
| 131 |
-
| M2 ULTRA | METAL | large-v2 | 1 | 0 | 222.
|
| 132 |
-
| M2 ULTRA | METAL | large-v2-q5_0 | 1 | 0 | 258.
|
| 133 |
-
| M2 ULTRA | METAL | large-v2-q5_1 | 1 | 0 | 258.
|
| 134 |
-
| M2 ULTRA | METAL | large-v2-q8_0 | 1 | 0 | 236.
|
| 135 |
-
| M2 ULTRA | METAL | large-v2-dis | 1 | 0 | 199.
|
| 136 |
-
| M2 ULTRA | METAL | large-v3-turbo | 1 | 0 | 201.
|
| 137 |
-
| M2 ULTRA | METAL | large-v3-turbo-q5_0 | 1 | 0 | 233.
|
| 138 |
-
| M2 ULTRA | METAL | large-v3-turbo-q8_0 | 1 | 0 | 214.
|
| 139 |
-
|
| 140 |
|
| 141 |
make -j && ./scripts/bench-all.sh 1 1 1
|
| 142 |
|
| 143 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 144 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 145 |
-
| M2 ULTRA | METAL | tiny | 1 | 1 | 7.
|
| 146 |
-
| M2 ULTRA | METAL | tiny-q5_0 | 1 | 1 | 8.
|
| 147 |
-
| M2 ULTRA | METAL | tiny-q5_1 | 1 | 1 | 8.
|
| 148 |
-
| M2 ULTRA | METAL | tiny-q8_0 | 1 | 1 | 7.
|
| 149 |
-
| M2 ULTRA | METAL | base | 1 | 1 | 13.
|
| 150 |
-
| M2 ULTRA | METAL | base-q5_0 | 1 | 1 |
|
| 151 |
-
| M2 ULTRA | METAL | base-q5_1 | 1 | 1 |
|
| 152 |
-
| M2 ULTRA | METAL | base-q8_0 | 1 | 1 | 14.
|
| 153 |
-
| M2 ULTRA | METAL | small | 1 | 1 |
|
| 154 |
-
| M2 ULTRA | METAL | small-q5_0 | 1 | 1 |
|
| 155 |
-
| M2 ULTRA | METAL | small-q5_1 | 1 | 1 |
|
| 156 |
-
| M2 ULTRA | METAL | small-q8_0 | 1 | 1 |
|
| 157 |
-
| M2 ULTRA | METAL | medium | 1 | 1 |
|
| 158 |
-
| M2 ULTRA | METAL | medium-q5_0 | 1 | 1 |
|
| 159 |
-
| M2 ULTRA | METAL | medium-q5_1 | 1 | 1 |
|
| 160 |
-
| M2 ULTRA | METAL | medium-q8_0 | 1 | 1 |
|
| 161 |
-
| M2 ULTRA | METAL | medium-dis | 1 | 1 |
|
| 162 |
-
| M2 ULTRA | METAL | large-v2 | 1 | 1 |
|
| 163 |
-
| M2 ULTRA | METAL | large-v2-q5_0 | 1 | 1 |
|
| 164 |
-
| M2 ULTRA | METAL | large-v2-q5_1 | 1 | 1 |
|
| 165 |
-
| M2 ULTRA | METAL | large-v2-q8_0 | 1 | 1 |
|
| 166 |
-
| M2 ULTRA | METAL | large-v2-dis | 1 | 1 |
|
| 167 |
-
| M2 ULTRA | METAL | large-v3-turbo | 1 | 1 |
|
| 168 |
-
| M2 ULTRA | METAL | large-v3-turbo-q5_0 | 1 | 1 |
|
| 169 |
-
| M2 ULTRA | METAL | large-v3-turbo-q8_0 | 1 | 1 |
|
| 170 |
|
| 171 |
|
| 172 |
## M4 Max
|
|
@@ -219,67 +218,69 @@ make -j && ./scripts/bench-all.sh 1 1 0
|
|
| 219 |
|
| 220 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 221 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 222 |
-
| M4 Max | METAL | tiny | 1 | 0 |
|
| 223 |
-
| M4 Max | METAL | tiny-q8_0 | 1 | 0 |
|
| 224 |
-
| M4 Max | METAL | base | 1 | 0 | 23.
|
| 225 |
-
| M4 Max | METAL | base-q8_0 | 1 | 0 |
|
| 226 |
-
| M4 Max | METAL | small | 1 | 0 | 71.
|
| 227 |
-
| M4 Max | METAL | small-q8_0 | 1 | 0 | 73.
|
| 228 |
-
| M4 Max | METAL | medium | 1 | 0 | 208.
|
| 229 |
-
| M4 Max | METAL | medium-q8_0 | 1 | 0 |
|
| 230 |
-
| M4 Max | METAL | large-v2 | 1 | 0 |
|
| 231 |
-
| M4 Max | METAL | large-v2-q8_0 | 1 | 0 |
|
|
|
|
| 232 |
|
| 233 |
|
| 234 |
make -j && ./scripts/bench-all.sh 1 1 1
|
| 235 |
|
| 236 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 237 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 238 |
-
| M4 Max | METAL | tiny | 1 | 1 |
|
| 239 |
-
| M4 Max | METAL | tiny-q8_0 | 1 | 1 |
|
| 240 |
-
| M4 Max | METAL | base | 1 | 1 |
|
| 241 |
-
| M4 Max | METAL | base-q8_0 | 1 | 1 |
|
| 242 |
-
| M4 Max | METAL | small | 1 | 1 |
|
| 243 |
-
| M4 Max | METAL | small-q8_0 | 1 | 1 |
|
| 244 |
-
| M4 Max | METAL | medium | 1 | 1 |
|
| 245 |
-
| M4 Max | METAL | medium-q8_0 | 1 | 1 |
|
| 246 |
-
| M4 Max | METAL | large-v2 | 1 | 1 |
|
| 247 |
-
| M4 Max | METAL | large-v2-q8_0 | 1 | 1 |
|
|
|
|
| 248 |
|
| 249 |
|
| 250 |
# V100
|
| 251 |
|
| 252 |
-
|
| 253 |
|
| 254 |
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 255 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 256 |
-
| V100 | AVX2 CUDA | tiny | 8 | 0 |
|
| 257 |
-
| V100 | AVX2 CUDA | tiny-q5_1 | 8 | 0 |
|
| 258 |
-
| V100 | AVX2 CUDA | base | 8 | 0 | 10.
|
| 259 |
-
| V100 | AVX2 CUDA | base-q5_1 | 8 | 0 |
|
| 260 |
-
| V100 | AVX2 CUDA | small | 8 | 0 | 31.
|
| 261 |
-
| V100 | AVX2 CUDA | small-q5_1 | 8 | 0 | 31.
|
| 262 |
-
| V100 | AVX2 CUDA | medium | 8 | 0 |
|
| 263 |
-
| V100 | AVX2 CUDA | medium-q5_0 | 8 | 0 |
|
| 264 |
-
| V100 | AVX2 CUDA | large-v2 | 8 | 0 |
|
| 265 |
-
| V100 | AVX2 CUDA | large-v2-q5_0 | 8 | 0 |
|
| 266 |
-
| V100 | AVX2 CUDA | large-v3-turbo | 8 | 0 |
|
| 267 |
-
| V100 | AVX2 CUDA | large-v3-turbo-q5_0 | 8 | 0 |
|
| 268 |
-
|
| 269 |
-
|
| 270 |
-
|
| 271 |
|
| 272 |
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 273 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 274 |
-
| V100 | AVX2 CUDA | tiny | 8 | 1 | 4.
|
| 275 |
-
| V100 | AVX2 CUDA | tiny-q5_1 | 8 | 1 | 4.
|
| 276 |
-
| V100 | AVX2 CUDA | base | 8 | 1 | 7.
|
| 277 |
-
| V100 | AVX2 CUDA | base-q5_1 | 8 | 1 | 7.
|
| 278 |
-
| V100 | AVX2 CUDA | small | 8 | 1 |
|
| 279 |
-
| V100 | AVX2 CUDA | small-q5_1 | 8 | 1 | 19.
|
| 280 |
-
| V100 | AVX2 CUDA | medium | 8 | 1 |
|
| 281 |
-
| V100 | AVX2 CUDA | medium-q5_0 | 8 | 1 |
|
| 282 |
-
| V100 | AVX2 CUDA | large-v2 | 8 | 1 |
|
| 283 |
-
| V100 | AVX2 CUDA | large-v2-q5_0 | 8 | 1 |
|
| 284 |
-
| V100 | AVX2 CUDA | large-v3-turbo | 8 | 1 |
|
| 285 |
-
| V100 | AVX2 CUDA | large-v3-turbo-q5_0 | 8 | 1 |
|
|
|
|
| 111 |
|
| 112 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 113 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 114 |
+
| M2 ULTRA | METAL | tiny | 1 | 0 | 10.15 | 1.20 | 0.36 | 0.01 | dc8dda60 |
|
| 115 |
+
| M2 ULTRA | METAL | tiny-q5_0 | 1 | 0 | 10.21 | 1.15 | 0.39 | 0.01 | dc8dda60 |
|
| 116 |
+
| M2 ULTRA | METAL | tiny-q5_1 | 1 | 0 | 9.26 | 1.15 | 0.38 | 0.01 | dc8dda60 |
|
| 117 |
+
| M2 ULTRA | METAL | tiny-q8_0 | 1 | 0 | 9.00 | 1.12 | 0.37 | 0.01 | dc8dda60 |
|
| 118 |
+
| M2 ULTRA | METAL | base | 1 | 0 | 15.77 | 1.73 | 0.45 | 0.02 | dc8dda60 |
|
| 119 |
+
| M2 ULTRA | METAL | base-q5_0 | 1 | 0 | 16.90 | 1.63 | 0.44 | 0.02 | dc8dda60 |
|
| 120 |
+
| M2 ULTRA | METAL | base-q5_1 | 1 | 0 | 16.93 | 1.64 | 0.44 | 0.02 | dc8dda60 |
|
| 121 |
+
| M2 ULTRA | METAL | base-q8_0 | 1 | 0 | 16.13 | 1.63 | 0.43 | 0.02 | dc8dda60 |
|
| 122 |
+
| M2 ULTRA | METAL | small | 1 | 0 | 45.15 | 3.45 | 0.92 | 0.05 | dc8dda60 |
|
| 123 |
+
| M2 ULTRA | METAL | small-q5_0 | 1 | 0 | 50.63 | 3.36 | 0.94 | 0.06 | dc8dda60 |
|
| 124 |
+
| M2 ULTRA | METAL | small-q5_1 | 1 | 0 | 50.56 | 3.36 | 0.94 | 0.06 | dc8dda60 |
|
| 125 |
+
| M2 ULTRA | METAL | small-q8_0 | 1 | 0 | 47.52 | 3.20 | 0.92 | 0.05 | dc8dda60 |
|
| 126 |
+
| M2 ULTRA | METAL | medium | 1 | 0 | 122.55 | 7.38 | 1.95 | 0.12 | dc8dda60 |
|
| 127 |
+
| M2 ULTRA | METAL | medium-q5_0 | 1 | 0 | 140.61 | 6.73 | 2.02 | 0.14 | dc8dda60 |
|
| 128 |
+
| M2 ULTRA | METAL | medium-q5_1 | 1 | 0 | 140.48 | 6.76 | 2.04 | 0.14 | dc8dda60 |
|
| 129 |
+
| M2 ULTRA | METAL | medium-q8_0 | 1 | 0 | 131.00 | 6.57 | 1.96 | 0.13 | dc8dda60 |
|
| 130 |
+
| M2 ULTRA | METAL | medium-dis | 1 | 0 | 110.85 | 1.00 | 0.24 | 0.02 | dc8dda60 |
|
| 131 |
+
| M2 ULTRA | METAL | large-v2 | 1 | 0 | 222.28 | 10.96 | 3.03 | 0.21 | dc8dda60 |
|
| 132 |
+
| M2 ULTRA | METAL | large-v2-q5_0 | 1 | 0 | 258.64 | 9.79 | 3.04 | 0.25 | dc8dda60 |
|
| 133 |
+
| M2 ULTRA | METAL | large-v2-q5_1 | 1 | 0 | 258.32 | 9.87 | 3.05 | 0.24 | dc8dda60 |
|
| 134 |
+
| M2 ULTRA | METAL | large-v2-q8_0 | 1 | 0 | 236.55 | 9.61 | 2.87 | 0.23 | dc8dda60 |
|
| 135 |
+
| M2 ULTRA | METAL | large-v2-dis | 1 | 0 | 199.84 | 1.14 | 0.27 | 0.02 | dc8dda60 |
|
| 136 |
+
| M2 ULTRA | METAL | large-v3-turbo | 1 | 0 | 201.52 | 1.77 | 0.45 | 0.03 | dc8dda60 |
|
| 137 |
+
| M2 ULTRA | METAL | large-v3-turbo-q5_0 | 1 | 0 | 233.14 | 1.56 | 0.47 | 0.04 | dc8dda60 |
|
| 138 |
+
| M2 ULTRA | METAL | large-v3-turbo-q8_0 | 1 | 0 | 214.23 | 1.53 | 0.44 | 0.04 | dc8dda60 |
|
|
|
|
| 139 |
|
| 140 |
make -j && ./scripts/bench-all.sh 1 1 1
|
| 141 |
|
| 142 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 143 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 144 |
+
| M2 ULTRA | METAL | tiny | 1 | 1 | 7.72 | 1.05 | 0.32 | 0.01 | dc8dda60 |
|
| 145 |
+
| M2 ULTRA | METAL | tiny-q5_0 | 1 | 1 | 8.20 | 0.98 | 0.31 | 0.01 | dc8dda60 |
|
| 146 |
+
| M2 ULTRA | METAL | tiny-q5_1 | 1 | 1 | 8.13 | 0.99 | 0.31 | 0.01 | dc8dda60 |
|
| 147 |
+
| M2 ULTRA | METAL | tiny-q8_0 | 1 | 1 | 7.96 | 0.93 | 0.30 | 0.01 | dc8dda60 |
|
| 148 |
+
| M2 ULTRA | METAL | base | 1 | 1 | 13.52 | 1.39 | 0.35 | 0.02 | dc8dda60 |
|
| 149 |
+
| M2 ULTRA | METAL | base-q5_0 | 1 | 1 | 14.88 | 1.31 | 0.34 | 0.02 | dc8dda60 |
|
| 150 |
+
| M2 ULTRA | METAL | base-q5_1 | 1 | 1 | 14.76 | 1.33 | 0.34 | 0.02 | dc8dda60 |
|
| 151 |
+
| M2 ULTRA | METAL | base-q8_0 | 1 | 1 | 14.04 | 1.28 | 0.34 | 0.02 | dc8dda60 |
|
| 152 |
+
| M2 ULTRA | METAL | small | 1 | 1 | 38.78 | 2.72 | 0.67 | 0.04 | dc8dda60 |
|
| 153 |
+
| M2 ULTRA | METAL | small-q5_0 | 1 | 1 | 44.01 | 2.64 | 0.69 | 0.05 | dc8dda60 |
|
| 154 |
+
| M2 ULTRA | METAL | small-q5_1 | 1 | 1 | 44.02 | 2.66 | 0.69 | 0.05 | dc8dda60 |
|
| 155 |
+
| M2 ULTRA | METAL | small-q8_0 | 1 | 1 | 40.79 | 2.49 | 0.67 | 0.05 | dc8dda60 |
|
| 156 |
+
| M2 ULTRA | METAL | medium | 1 | 1 | 104.48 | 5.57 | 1.61 | 0.10 | dc8dda60 |
|
| 157 |
+
| M2 ULTRA | METAL | medium-q5_0 | 1 | 1 | 122.24 | 5.00 | 1.58 | 0.12 | dc8dda60 |
|
| 158 |
+
| M2 ULTRA | METAL | medium-q5_1 | 1 | 1 | 121.99 | 5.02 | 1.59 | 0.12 | dc8dda60 |
|
| 159 |
+
| M2 ULTRA | METAL | medium-q8_0 | 1 | 1 | 111.68 | 4.99 | 1.52 | 0.11 | dc8dda60 |
|
| 160 |
+
| M2 ULTRA | METAL | medium-dis | 1 | 1 | 93.23 | 0.87 | 0.21 | 0.01 | dc8dda60 |
|
| 161 |
+
| M2 ULTRA | METAL | large-v2 | 1 | 1 | 189.82 | 8.36 | 2.35 | 0.19 | dc8dda60 |
|
| 162 |
+
| M2 ULTRA | METAL | large-v2-q5_0 | 1 | 1 | 225.73 | 7.34 | 2.40 | 0.22 | dc8dda60 |
|
| 163 |
+
| M2 ULTRA | METAL | large-v2-q5_1 | 1 | 1 | 225.88 | 7.60 | 2.40 | 0.22 | dc8dda60 |
|
| 164 |
+
| M2 ULTRA | METAL | large-v2-q8_0 | 1 | 1 | 203.55 | 7.32 | 2.26 | 0.20 | dc8dda60 |
|
| 165 |
+
| M2 ULTRA | METAL | large-v2-dis | 1 | 1 | 168.20 | 0.98 | 0.24 | 0.02 | dc8dda60 |
|
| 166 |
+
| M2 ULTRA | METAL | large-v3-turbo | 1 | 1 | 170.22 | 1.46 | 0.37 | 0.03 | dc8dda60 |
|
| 167 |
+
| M2 ULTRA | METAL | large-v3-turbo-q5_0 | 1 | 1 | 201.88 | 1.27 | 0.38 | 0.04 | dc8dda60 |
|
| 168 |
+
| M2 ULTRA | METAL | large-v3-turbo-q8_0 | 1 | 1 | 182.37 | 1.24 | 0.36 | 0.03 | dc8dda60 |
|
| 169 |
|
| 170 |
|
| 171 |
## M4 Max
|
|
|
|
| 218 |
|
| 219 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 220 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 221 |
+
| M4 Max | METAL | tiny | 1 | 0 | 12.83 | 0.94 | 0.30 | 0.01 | dc8dda60 |
|
| 222 |
+
| M4 Max | METAL | tiny-q8_0 | 1 | 0 | 12.95 | 0.80 | 0.31 | 0.01 | dc8dda60 |
|
| 223 |
+
| M4 Max | METAL | base | 1 | 0 | 23.54 | 1.37 | 0.33 | 0.02 | dc8dda60 |
|
| 224 |
+
| M4 Max | METAL | base-q8_0 | 1 | 0 | 24.14 | 1.24 | 0.33 | 0.02 | dc8dda60 |
|
| 225 |
+
| M4 Max | METAL | small | 1 | 0 | 71.59 | 3.02 | 0.71 | 0.06 | dc8dda60 |
|
| 226 |
+
| M4 Max | METAL | small-q8_0 | 1 | 0 | 73.34 | 2.65 | 0.72 | 0.06 | dc8dda60 |
|
| 227 |
+
| M4 Max | METAL | medium | 1 | 0 | 208.53 | 7.02 | 1.58 | 0.16 | dc8dda60 |
|
| 228 |
+
| M4 Max | METAL | medium-q8_0 | 1 | 0 | 212.87 | 6.00 | 1.58 | 0.17 | dc8dda60 |
|
| 229 |
+
| M4 Max | METAL | large-v2 | 1 | 0 | 379.84 | 11.47 | 2.52 | 0.29 | dc8dda60 |
|
| 230 |
+
| M4 Max | METAL | large-v2-q8_0 | 1 | 0 | 390.45 | 9.19 | 2.48 | 0.29 | dc8dda60 |
|
| 231 |
+
| M4 Max | METAL | large-v3-turbo | 1 | 0 | 345.74 | 1.99 | 0.44 | 0.05 | dc8dda60 |
|
| 232 |
|
| 233 |
|
| 234 |
make -j && ./scripts/bench-all.sh 1 1 1
|
| 235 |
|
| 236 |
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 237 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 238 |
+
| M4 Max | METAL | tiny | 1 | 1 | 11.70 | 0.74 | 0.23 | 0.01 | dc8dda60 |
|
| 239 |
+
| M4 Max | METAL | tiny-q8_0 | 1 | 1 | 12.36 | 0.67 | 0.23 | 0.01 | dc8dda60 |
|
| 240 |
+
| M4 Max | METAL | base | 1 | 1 | 21.76 | 1.12 | 0.25 | 0.02 | dc8dda60 |
|
| 241 |
+
| M4 Max | METAL | base-q8_0 | 1 | 1 | 22.60 | 0.94 | 0.26 | 0.02 | dc8dda60 |
|
| 242 |
+
| M4 Max | METAL | small | 1 | 1 | 67.26 | 2.27 | 0.50 | 0.06 | dc8dda60 |
|
| 243 |
+
| M4 Max | METAL | small-q8_0 | 1 | 1 | 68.67 | 1.93 | 0.53 | 0.06 | dc8dda60 |
|
| 244 |
+
| M4 Max | METAL | medium | 1 | 1 | 193.58 | 5.31 | 1.20 | 0.16 | dc8dda60 |
|
| 245 |
+
| M4 Max | METAL | medium-q8_0 | 1 | 1 | 198.60 | 4.31 | 1.21 | 0.16 | dc8dda60 |
|
| 246 |
+
| M4 Max | METAL | large-v2 | 1 | 1 | 357.54 | 8.73 | 1.99 | 0.27 | dc8dda60 |
|
| 247 |
+
| M4 Max | METAL | large-v2-q8_0 | 1 | 1 | 363.98 | 6.43 | 1.99 | 0.28 | dc8dda60 |
|
| 248 |
+
| M4 Max | METAL | large-v3-turbo | 1 | 1 | 322.32 | 1.66 | 0.37 | 0.05 | dc8dda60 |
|
| 249 |
|
| 250 |
|
| 251 |
# V100
|
| 252 |
|
| 253 |
+
GGML_CUDA=1 make -j && ./scripts/bench-all.sh 8 1 0
|
| 254 |
|
| 255 |
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 256 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 257 |
+
| V100 | AVX2 CUDA | tiny | 8 | 0 | 5.99 | 1.01 | 0.30 | 0.01 | dc8dda60 |
|
| 258 |
+
| V100 | AVX2 CUDA | tiny-q5_1 | 8 | 0 | 6.07 | 1.00 | 0.26 | 0.01 | dc8dda60 |
|
| 259 |
+
| V100 | AVX2 CUDA | base | 8 | 0 | 10.96 | 1.44 | 0.43 | 0.02 | dc8dda60 |
|
| 260 |
+
| V100 | AVX2 CUDA | base-q5_1 | 8 | 0 | 11.11 | 1.41 | 0.37 | 0.02 | dc8dda60 |
|
| 261 |
+
| V100 | AVX2 CUDA | small | 8 | 0 | 31.04 | 2.84 | 0.86 | 0.04 | dc8dda60 |
|
| 262 |
+
| V100 | AVX2 CUDA | small-q5_1 | 8 | 0 | 31.69 | 2.82 | 0.71 | 0.04 | dc8dda60 |
|
| 263 |
+
| V100 | AVX2 CUDA | medium | 8 | 0 | 83.95 | 6.05 | 1.82 | 0.09 | dc8dda60 |
|
| 264 |
+
| V100 | AVX2 CUDA | medium-q5_0 | 8 | 0 | 85.86 | 5.58 | 1.45 | 0.10 | dc8dda60 |
|
| 265 |
+
| V100 | AVX2 CUDA | large-v2 | 8 | 0 | 138.50 | 8.70 | 2.71 | 0.15 | dc8dda60 |
|
| 266 |
+
| V100 | AVX2 CUDA | large-v2-q5_0 | 8 | 0 | 142.31 | 7.82 | 2.03 | 0.16 | dc8dda60 |
|
| 267 |
+
| V100 | AVX2 CUDA | large-v3-turbo | 8 | 0 | 128.39 | 1.42 | 0.44 | 0.02 | dc8dda60 |
|
| 268 |
+
| V100 | AVX2 CUDA | large-v3-turbo-q5_0 | 8 | 0 | 131.24 | 1.17 | 0.33 | 0.03 | dc8dda60 |
|
| 269 |
+
|
| 270 |
+
|
| 271 |
+
GGML_CUDA=1 make -j && ./scripts/bench-all.sh 8 1 1
|
| 272 |
|
| 273 |
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
|
| 274 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 275 |
+
| V100 | AVX2 CUDA | tiny | 8 | 1 | 4.85 | 0.97 | 0.26 | 0.01 | dc8dda60 |
|
| 276 |
+
| V100 | AVX2 CUDA | tiny-q5_1 | 8 | 1 | 4.97 | 0.89 | 0.19 | 0.01 | dc8dda60 |
|
| 277 |
+
| V100 | AVX2 CUDA | base | 8 | 1 | 7.23 | 1.28 | 0.35 | 0.02 | dc8dda60 |
|
| 278 |
+
| V100 | AVX2 CUDA | base-q5_1 | 8 | 1 | 7.38 | 1.24 | 0.26 | 0.02 | dc8dda60 |
|
| 279 |
+
| V100 | AVX2 CUDA | small | 8 | 1 | 20.87 | 2.44 | 0.71 | 0.03 | dc8dda60 |
|
| 280 |
+
| V100 | AVX2 CUDA | small-q5_1 | 8 | 1 | 19.80 | 2.35 | 0.51 | 0.03 | dc8dda60 |
|
| 281 |
+
| V100 | AVX2 CUDA | medium | 8 | 1 | 54.56 | 5.31 | 1.46 | 0.06 | dc8dda60 |
|
| 282 |
+
| V100 | AVX2 CUDA | medium-q5_0 | 8 | 1 | 56.09 | 4.67 | 1.05 | 0.07 | dc8dda60 |
|
| 283 |
+
| V100 | AVX2 CUDA | large-v2 | 8 | 1 | 87.05 | 7.65 | 2.16 | 0.10 | dc8dda60 |
|
| 284 |
+
| V100 | AVX2 CUDA | large-v2-q5_0 | 8 | 1 | 94.65 | 6.60 | 1.47 | 0.11 | dc8dda60 |
|
| 285 |
+
| V100 | AVX2 CUDA | large-v3-turbo | 8 | 1 | 76.46 | 1.29 | 0.37 | 0.02 | dc8dda60 |
|
| 286 |
+
| V100 | AVX2 CUDA | large-v3-turbo-q5_0 | 8 | 1 | 79.62 | 1.03 | 0.23 | 0.02 | dc8dda60 |
|