RTX A6000 48GBBudget pickC27.3 tok/s decode
~$4,650 MSRP
Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
16.1 tok/s
TTFT
12016 ms
Safe context
21K
Memory
34.9 GB / 46.1 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 16.1 tok/s | 17478 ms | 36K |
| Chat | C | Runs well | 16.1 tok/s | 6554 ms | 11K |
| Coding | C | Runs well | 16.1 tok/s | 12016 ms | 21K |
| RAG | C | Tight fit | 16.1 tok/s | 21848 ms | 36K |
| Reasoning | C | Runs well | 16.1 tok/s | 14201 ms | 21K |
How Qwen3.5 35B A3B (35B params) fits at each quantization level on MacBook Pro M4 Max 64GB (46.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | D36 |
Q3_K_S | 3 | 17.2 GB | Low | D37 |
NVFP4 | 4 | 19.6 GB | Medium | D38 |
Q4_K_M | 4 | 21.3 GB | Medium | D39 |
Q5_K_M | 5 | 25.2 GB | High | C41 |
Q6_K | 6 | 28.7 GB | High | C43 |
Q8_0Best for your GPU | 8 | 37.5 GB | Very High | C44 |
F16 | 16 | 71.8 GB | Maximum | F0 |
huggingface-cli download hf-lmstudio-community--qwen3-5-35b-a3b-ggufUpgrade options
RTX A6000 48GBBudget pick~$4,650 MSRP
NVIDIA L40 48GBBest value~$5,500 MSRP
RTX PRO 5000 Blackwell 48GBBiggest leap