eaddario/Watt-Tool-8B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: eaddario/Watt-Tool-8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 16:00:13 +08:00
commit f9723b838e
110 changed files with 14825 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
scores/Watt-Tool-8B-q6_k.arc Normal file
View File

@@ -0,0 +1,13 @@
build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q6_K.gguf (version GGUF V3 (latest))
Final result: 66.1333 +/- 1.7292
Random chance: 25.0083 +/- 1.5824
llama_perf_context_print: load time = 2966.80 ms
llama_perf_context_print: prompt eval time = 121882.40 ms / 36600 tokens ( 3.33 ms per token, 300.29 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 122783.42 ms / 36601 tokens
ggml_metal_free: deallocating