Zhipu on NVIDIA Ampere
Can I run GLM-4 9B on an RTX 3060 12GB?
Yes. GLM-4 9B at Q4_K_M uses 6.5 GB of the 10.5 GB available on a RTX 3060 12GB, and runs at about 40.2 tokens per second. You can push the context to 109K.
Runs comfortably
6.5 GB of 10.5 GB · 62%010 GB
Weights
5.4 GB
KV cache
0.3 GB
Runtime overhead
0.8 GB
GLM-4 9B at Q4_K_M leaves 3.9 GB spare on a RTX 3060 12GB. There is room to raise the context length or move up a quantisation level.
Generation40.2tok/s
Prompt processing559tok/s
Max context109Ktokens
KV per 1K tokens0GB
Every quantisation of GLM-4 9B on a RTX 3060 12GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 17.5 GB | 18.6 GB | Won't fit | — | 3.98 |
| INT8 / W8A8 | 8.50 | 9.0 GB | 10.2 GB | Fits, but tight | 16K | 24.4 |
| Q8_0 (GGUF) | 8.50 | 9.0 GB | 10.2 GB | Fits, but tight | 16K | 24.4 |
| FP8 (E4M3) | 8.00 | 8.8 GB | 9.9 GB | Fits, but tight | 23K | 25.1 |
| Q6_K | 6.56 | 7.2 GB | 8.3 GB | Runs comfortably | 64K | 30.5 |
| AWQ 4-bit | 4.25 | 6.3 GB | 7.5 GB | Runs comfortably | 85K | 34.4 |
| GPTQ 4-bit | 4.25 | 6.3 GB | 7.5 GB | Runs comfortably | 85K | 34.4 |
| MXFP4 | 4.25 | 6.3 GB | 7.5 GB | Runs comfortably | 85K | 34.4 |
| Q5_K_M | 5.67 | 6.2 GB | 7.3 GB | Runs comfortably | 88K | 35.1 |
| Q5_K_S | 5.52 | 6.0 GB | 7.2 GB | Runs comfortably | 93K | 36.0 |
| Q4_K_M | 4.85 | 5.4 GB | 6.5 GB | Runs comfortably | 109K | 40.2 |
| Q4_K_S | 4.58 | 5.1 GB | 6.3 GB | Runs comfortably | 116K | 42.1 |
| Q4_0 | 4.55 | 5.1 GB | 6.2 GB | Runs comfortably | 116K | 42.3 |
| IQ4_XS | 4.25 | 4.8 GB | 6.0 GB | Runs comfortably | 124K | 44.7 |
| Q3_K_M | 3.91 | 4.5 GB | 5.6 GB | Runs comfortably | 128K | 47.8 |
| IQ3_M | 3.70 | 4.3 GB | 5.4 GB | Runs comfortably | 128K | 49.9 |
| IQ3_XXS | 3.06 | 3.7 GB | 4.8 GB | Runs comfortably | 128K | 57.6 |
| Q2_K | 2.63 | 3.3 GB | 4.4 GB | Runs comfortably | 128K | 64.3 |
| IQ2_XXS | 2.06 | 2.8 GB | 3.9 GB | Runs comfortably | 128K | 76.1 |
| IQ1_M | 1.75 | 2.5 GB | 3.6 GB | Runs comfortably | 128K | 84.5 |