julian/amd-strix-halo-toolboxes
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

add minimax m2.7 benchmarks

Browse Source
This commit is contained in:
Donato Capitella
2026-04-15 08:08:43 +01:00
parent 4b3c02a405
commit 14fae26ad0
11 changed files with 645 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__rocm-7_2_1__fa1.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 1 | 0 | pp512 | 245.94 ± 1.48 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 1 | 0 | tg128 | 24.11 ± 0.05 |
build: ff5ef8278 (8763)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__rocm-7_2_1__fa1__longctx32768.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 66.09 ± 0.53 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 6.32 ± 0.05 |
build: ff5ef8278 (8763)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__rocm6_4_4__fa1.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 1 | 0 | pp512 | 245.63 ± 1.62 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 1 | 0 | tg128 | 22.63 ± 0.07 |
build: 3f8752b55 (8743)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__rocm6_4_4__fa1__longctx32768.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 79.52 ± 0.47 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 6.69 ± 0.15 |
build: 3f8752b55 (8743)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__rocm7-nightlies__fa1.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 1 | 0 | pp512 | 237.43 ± 0.96 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 1 | 0 | tg128 | 22.63 ± 0.05 |
build: 3f8752b55 (8743)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__rocm7-nightlies__fa1__longctx32768.log
+8
View File
@@ -0,0 +1,8 @@
ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 61.53 ± 0.27 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 6.52 ± 0.17 |
build: 3f8752b55 (8743)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__vulkan_amdvlk__fa1.log
+8
View File
@@ -0,0 +1,8 @@
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | pp512 | 203.53 ± 0.70 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | tg128 | 24.06 ± 0.03 |
build: 3f8752b55 (8743)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__vulkan_amdvlk__fa1__longctx32768.log
+8
View File
@@ -0,0 +1,8 @@
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | pp2048 @ d32768 | 31.94 ± 0.07 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | tg32 @ d32768 | 10.05 ± 0.01 |
build: 3f8752b55 (8743)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__vulkan_radv__fa1.log
+8
View File
@@ -0,0 +1,8 @@
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | pp512 | 234.24 ± 1.27 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | tg128 | 29.48 ± 0.01 |
build: 3f8752b55 (8743)
benchmark/results/MiniMax-M2.7-UD-Q3_K_XL-00001-of-00004__vulkan_radv__fa1__longctx32768.log
+8
View File
@@ -0,0 +1,8 @@
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | pp2048 @ d32768 | 32.31 ± 0.16 |
| minimax-m2 230B.A10B Q3_K - Medium | 94.93 GiB | 228.69 B | Vulkan | 99 | 1 | 0 | tg32 @ d32768 | 14.20 ± 0.01 |
build: 3f8752b55 (8743)