Can it run?
Runs well
Using Q6_K in Ollama
Fit status
Runs well
Decode
231.0 tok/s
TTFT
838 ms
Safe context
65K
Memory
5.7 GB / 23.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 231.0 tok/s | 1219 ms | 129K |
| Chat | C | Runs well | 231.0 tok/s | 457 ms | 32K |
| Coding | C | Runs well | 231.0 tok/s | 838 ms | 65K |
| RAG | C | Runs well | 231.0 tok/s | 1524 ms | 129K |
| Reasoning | C | Runs well | 231.0 tok/s | 990 ms | 65K |
How embeddinggemma 300M (0.30000001192092896B params) fits at each quantization level on MacBook Pro M1 Max 32GB (23.0 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 | D30 |
Q4_K_M | 4 | 0.2 GB | Medium | D30 |
Q5_K_M | 5 | 0.2 GB | High | D30 |
Q6_K | 6 | 0.2 GB | High | D30 |
Q8_0 | 8 | 0.3 GB | Very High | D30 |
F16Best for your GPU | 16 | 0.6 GB | Maximum | D30 |
huggingface-cli download hf-ggml-org--embeddinggemma-300m-gguf