Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
25.9 tok/s
TTFT
7475 ms
Safe context
23K
Memory
32.8 GB / 48.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 27.3 tok/s | 10300 ms | 40K |
| Chat | C | Runs well | 27.3 tok/s | 3863 ms | 13K |
| Coding | C | Runs well | 25.9 tok/s | 7475 ms | 23K |
| RAG | C | Runs well | 27.3 tok/s | 12876 ms | 40K |
| Reasoning | C | Runs well | 27.3 tok/s | 8369 ms | 23K |
How Qwen3.5 35B A3B (35B params) fits at each quantization level on RTX A6000 48GB (48.0 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 |
huggingface-cli download hf-unsloth--qwen3-5-35b-a3b-gguf19.6 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 | C42 |
Q8_0Best for your GPU | 8 | 37.5 GB | Very High | C45 |
F16 | 16 | 71.8 GB | Maximum | F0 |