Can it run?
Runs well
Using Q6_K in Ollama
Fit status
Runs well
Decode
95.9 tok/s
TTFT
2019 ms
Safe context
23K
Memory
4.2 GB / 6.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 95.9 tok/s | 2937 ms | 45K |
| Chat | B | Runs well | 95.9 tok/s | 1101 ms | 11K |
| Coding | B | Runs well | 95.9 tok/s | 2019 ms | 23K |
| RAG | B | Runs well | 95.9 tok/s | 3671 ms | 45K |
| Reasoning | B | Runs well | 95.9 tok/s | 2386 ms | 23K |
How gemma 2 2b it (2B params) fits at each quantization level on RX 5600 XT 6GB (6.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.8 GB | Low | D32 |
Q3_K_S | 3 | 1.0 GB | Low | D33 |
NVFP4 | 4 | 1.1 GB | Medium | D33 |
Q4_K_M | 4 | 1.2 GB | Medium | D34 |
Q5_K_M | 5 | 1.4 GB | High | D35 |
Q6_K | 6 | 1.6 GB | High | D35 |
Q8_0Best for your GPU | 8 | 2.1 GB | Very High | D37 |
F16 | 16 | 4.1 GB | Maximum | C44 |
huggingface-cli download hf-bartowski--gemma-2-2b-it-gguf