Can I run it?
Can I run Tiel Coder 35B A3B on Apple M4 Pro?
Tight fit
Tight fit fully in unified memory on your Apple M4 Pro at UD-IQ4_XS, 8K context, about 88–120 tok/s. Weights 16.5 GB plus 0.19 GB of KV cache — 17.2 GB of 18.0 GB usable. Up to 32K context still fits.
Best quantUD-IQ4_XS
Working context8K
Max that fits32K
Speed88–120 tok/s
Weights16.5 GB
KV cache0.19 GB
Total17.2 GB
Usable18.0 GB
Tiel Coder 35B A3B details · Apple M4 Pro page · How this estimate is made
Run commands
llama.cpp
llama-server -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-IQ4_XS -c 8192 -ngl 40
No matching name in the Ollama library snapshot.
LM Studio
lms get peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF # Then load quant UD-IQ4_XS
Assumptions
- Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- UD-IQ4_XS size is the real GGUF file size from Hugging Face.
- Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on Apple M4 Pro? — Tight fit, UD-IQ4_XS, 88–120 tok/s
- Can I run Qwen3.8 35B A3B Distill on Apple M4 Pro? — Tight fit, Q3_K_M, 90–123 tok/s
- Can I run Qwen3.5 35B A3B on Apple M4 Pro? — Tight fit, UD-IQ4_XS, 89–122 tok/s
Updated 2026-10-24. Profile on this page is the device default.