Updated benchmarks
This commit is contained in:
@@ -2,7 +2,7 @@ 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 |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | pp512 | 732.35 ± 7.51 |
|
||||
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | tg128 | 72.05 ± 0.07 |
|
||||
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | pp512 | 1204.49 ± 13.52 |
|
||||
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | Vulkan | 99 | 1 | 0 | tg128 | 74.94 ± 0.14 |
|
||||
|
||||
build: 1fe00296 (6182)
|
||||
build: f1fbffb5 (6486)
|
||||
|
||||
Reference in New Issue
Block a user