Can Ornith 1.0 35B-A3B run on HONOR Robot Phone?
NO — Won't fit
Formula estimate
What this means
None of the versions we checked fit safely on this phone. The checked version needs about 25.3 GB, while we estimate that the model can use about 12 GB.
Try a smaller model, or use this model on a device with more memory.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
−13.3GB short
memory that doesn't exist here
25.3GB
needed at Q4_K_M
Q4_K_M
quant checked
needs 25.3 GBusable 12 GB · short 13.3 GB
Snapdragon 8 Elite Gen 516 GB RAMCPU / GPU
Three ways forward
1
Try a smaller quant
No quant of Ornith 1.0 35B-A3B fits this phone — even the smallest is too big. Options 2 and 3 are your real choices.
2
Same family, smaller
grug 9B (ProCreations) · Q4_K_M · 5.9 GB
! ~6.5 tokens/s here
check grug 9B (ProCreations) →3
Run it in the cloud
The full Ornith 1.0 35B-A3B, no download, at data-center speed — pay per token.
provider recommendations coming later
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q4_K_M GGUF (21.2 GB) + mmap overhead | 22.3 |
| KV cache | 4K context window | 2.5 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q4_K_M, 4K context | 25.3 |
| Working budget | 16 GB RAM − Android system reserve | 12 |
| Headroom | memory shortfall | −13.3 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q4_K_M | 21.2 GB | ✕ Won't fit | won't fit |
| Q5_K_M | 24.7 GB | ✕ Won't fit | won't fit |
| Q6_K | 28.5 GB | ✕ Won't fit | won't fit |
| Q8_0 | 36.9 GB | ✕ Won't fit | won't fit |
Related checks
More on HONOR Robot Phone
Ornith 1.0 35B-A3B on other phones