NVIDIA A100 80GBBudget pickC80.2 tok/s decode
~$15,000 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
29K
Memory
38.4 GB / 69.1 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 16.1 tok/s | 17478 ms | 50K |
| Chat | C | Runs well | 16.1 tok/s | 6554 ms | 16K |
| Coding | C | Runs well | 16.1 tok/s | 12016 ms | 29K |
| RAG | C | Runs well | 16.1 tok/s | 21848 ms | 50K |
| Reasoning | C | Runs well | 16.1 tok/s | 14201 ms | 29K |
How Qwen3.5 35B A3B (35B params) fits at each quantization level on MacBook Pro M4 Max 96GB (69.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | D34 |
Q3_K_S | 3 | 17.2 GB | Low | D35 |
NVFP4 | 4 | 19.6 GB | Medium | D35 |
Q4_K_M | 4 | 21.3 GB | Medium | D36 |
Q5_K_M | 5 | 25.2 GB | High | D37 |
Q6_K | 6 | 28.7 GB | High | D38 |
Q8_0Best for your GPU | 8 | 37.5 GB | Very High | C41 |
F16 | 16 | 71.8 GB | Maximum | F0 |
huggingface-cli download hf-lmstudio-community--qwen3-5-35b-a3b-ggufUpgrade options
NVIDIA A100 80GBBudget pick~$15,000 MSRP
~$15,000 MSRP
NVIDIA H100 80GBBiggest leap~$40,000 MSRP