Can it run?
Runs well
Using Q6_K in Ollama
Fit status
Runs well
Decode
252.0 tok/s
TTFT
768 ms
Safe context
92K
Memory
16.1 GB / 92.2 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 252.0 tok/s | 1117 ms | 184K |
| Chat | C | Runs well | 252.0 tok/s | 419 ms | 46K |
| Coding | C | Runs well | 252.0 tok/s | 768 ms | 92K |
| RAG | C | Runs well | 252.0 tok/s | 1397 ms | 184K |
| Reasoning | C | Runs well | 252.0 tok/s | 908 ms | 92K |
How embeddinggemma 300M (0.30000001192092896B params) fits at each quantization level on MacBook Pro M3 Max 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.1 GB | Low | D29 |
Q3_K_S | 3 | 0.1 GB | Low | D29 |
NVFP4 | 4 | 0.2 GB | Medium | D29 |
Q4_K_M | 4 | 0.2 GB | Medium | D29 |
Q5_K_M | 5 | 0.2 GB | High | D29 |
Q6_K | 6 | 0.2 GB | High | D29 |
Q8_0 | 8 | 0.3 GB | Very High | D29 |
F16Best for your GPU | 16 | 0.6 GB | Maximum | D30 |
huggingface-cli download hf-ggml-org--embeddinggemma-300m-gguf