llama.cpp on the AMD Radeon 780M
On the AMD Radeon 780M, llama.cpp runs Qwen3.6 35B · 3B active at 8-bit at a median 19.7 tokens per second for generation, from 2 plain runs (context not stated).
Speed by model on the AMD Radeon 780M
Plain runs only: one device, one request, no speculative decoding, the whole model in memory. Each row is one model size at one bit class, with the other engines' plain runs of the same model on this card beside it. Context length and build still differ between runs, and each side shows its own.
| Model | llama.cpp | Other engines |
|---|---|---|
| Qwen3.6 35B · 3B active 8-bit | 19.7 t/smedian of 2, context not stated | no other engine reported |
| Gemma 4 26B · 4B active 4-bit | 25.0 t/sone report, context not stated | no other engine reported |
4 llama.cpp reports on the AMD Radeon 780M
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Gemma 4 26B · 4B active · Q4_K_M25.0 t/s
- Qwen3.6 35B · 3B active · Q8_021.1 t/s
- Qwen3.6 35B · 3B active · Q818.4 t/s
- Qwen3.8PP 100.0 t/s
Frequently asked
How fast is llama.cpp on the AMD Radeon 780M?
On the AMD Radeon 780M, llama.cpp runs Qwen3.6 35B · 3B active at 8-bit at a median 19.7 tokens per second for generation, from 2 plain runs (context not stated).