Task LLM generation · model-size class LLM 5–14B · batch 1 · 19 platforms · model filter "llama 2 7b"
✓ Like-for-like: same model-size class and batch.
| Platform | Result | Model · precision · stack | Grade | Power | Price | Fit perf/power/budget | Source |
|---|---|---|---|---|---|---|---|
| Apple M5 Ultra (80-core GPU, 1228 GB/s) | 179 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit c1d0e7a) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| Apple M5 Max (40-core GPU, 614 GB/s) | 120 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit c1d0e7a) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| AMD Ryzen AI Max+ (Strix Halo) iGPU | 54.38 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit fb4b273) | C | 120 W platform spec envelope (not measured with this result) | $3999 | yes / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| Apple M3 Ultra iGPU | 116 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA off, commit 2d451c8) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| NVIDIA DGX Spark | 60.39 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit 657e011) | C | 153 W platform spec envelope (not measured with this result) | $4699 | yes / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| Apple M4 Max (40-core GPU, 546 GB/s) | 83.06 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit 8e672ef) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| Apple M4 Max iGPU | 75.02 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA off, commit 1ece0cb6) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| Apple M4 Max (32-core GPU, 410 GB/s) | 69.95 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit 8e672ef) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| Apple M5 Pro (16-core GPU, 307 GB/s) | 67.59 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit 60081bb) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| Apple M5 Pro (20-core GPU, 307 GB/s) | 66.33 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit c1d0e7a) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| Apple M4 Pro (20-core GPU, 273 GB/s) | 50.74 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit 8e672ef) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| Apple M4 Pro (16-core GPU, 273 GB/s) | 49.64 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit 8e672ef) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| Intel Core Ultra 200 Series iGPU | 25.12 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit 4a89937) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| Intel Core Ultra 300 Series iGPU | 24.45 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA off, commit 481c65f) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| Apple M4 (10-core GPU, 120 GB/s) | 24.11 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Metal (commit 8e672ef) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #4167 scoreboard (via GitHub API) |
| AMD Ryzen AI 300 Series iGPU | 23.93 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit N/A) | C | unknown no power published | unknown | yes / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| AMD Ryzen AI 400 Series iGPU | 19.03 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit cb26014) | C | unknown no power published | unknown | no / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| MediaTek Dimensity 9400 iGPU | 8.92 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA off, commit b9ab0a4) | C | unknown no power published | unknown | no / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
| Intel Core Ultra 100 Series iGPU | 8.21 tok/s tg128 b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA off, commit 1d72c84) | C | unknown no power published | unknown | no / – / – | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) |
Confidence: A audited MLPerf closed, B documented third-party, C community, D vendor-published, E estimate. Unknown is never assumed. Other like-for-like groups: LLM 5–14B b1 (19)