Can the MacBook Pro 16" M4 Max run Qwen3.8-27B-OBLITERATED?
Yes. Qwen3.8-27B-OBLITERATED fits the MacBook Pro 16" M4 Max's 48 GB at Q4_K_M (about 17.8 GB needed), running at an estimated 20 tok/s. There's room for up to Q8_0 if you want higher quality.
Every quantization
Qwen3.8-27B-OBLITERATED (27.8B) on 48 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 16 GB | 17.8 GB | Fits easily | ~20 tok/s |
| Q5_K_M | 20 GB | 21.8 GB | Fits easily | ~16 tok/s |
| Q8_0 | 30 GB | 31.8 GB | Fits | ~10 tok/s |
| FP16 | 56 GB | 57.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the MacBook Pro 16" M4 Max's 546 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf mradermacher/Qwen3.8-27B-OBLITERATED-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Qwen3.8-27B-OBLITERATED details →
Compare
Same model, other hardware - and other models on this card
Qwen3.8-27B-OBLITERATED on other hardware
- RTX 5090~64 tok/s
- RTX 5090 D~64 tok/s
- RTX 6000D~56 tok/s
- RTX 4090~39 tok/s
- RTX 3090~34 tok/s
- Radeon RX 7900 XTX~34 tok/s
- Arc Pro B60~16 tok/s
- DGX Spark (GB10)~9.8 tok/s
Also runs on the MacBook Pro 16" M4 Max
- deepseek-v4-flash-0731-spark~8.9 tok/s
- Qwen3.6 35B A3B~119 tok/s
- dolphin-2.9.1-yi-1.5-34b~16 tok/s
- Laguna-XS-2.1~16 tok/s
- Gemma 4 31B~16 tok/s
- OTel-2.0-LLM-31B-IT~16 tok/s
- Qwen3 32B~16 tok/s
- OTel-2.0-LLM-31B-IT-QLoRA~17 tok/s
Frequently asked
Quick answers
Can the Apple MacBook Pro 16" M4 Max run Qwen3.8-27B-OBLITERATED?
Yes. Qwen3.8-27B-OBLITERATED fits the MacBook Pro 16" M4 Max's 48 GB at Q4_K_M (about 17.8 GB needed), running at an estimated 20 tok/s. There's room for up to Q8_0 if you want higher quality.
How much VRAM does Qwen3.8-27B-OBLITERATED need?
About 16 GB of weights at Q4_K_M, 30 GB at Q8_0 and 56 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Qwen3.8-27B-OBLITERATED on the MacBook Pro 16" M4 Max?
Roughly 20 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the MacBook Pro 16" M4 Max's 546 GB/s memory bandwidth.