Hardware › HP Z2 Mini G1a (Ryzen AI Max PRO 390) 64GB
HP Z2 Mini G1a (Ryzen AI Max PRO 390) 64GB for local AI: price in Australia & what it can run
A$5,894cheapest found · Mwave
64 GBunified (48.0 GB usable)
256 GB/smemory bandwidth
50 tok/sestimated, Llama 2 7B Q4_0
View at Mwave → Price checked 20 Oct 2026, 7:44 am AEST.
The 390 has a smaller GPU than the 395; no scoreboard entry, so speed is a bandwidth estimate.
Benchmark
No public benchmark found for this exact hardware. Speeds on this page are bandwidth-based estimates using a median efficiency of 74%.
Specs: AMD Ryzen AI Max PRO 390: 256-bit LPDDR5X-8000 (manually entered)
AU prices found
| Retailer | Listing | Price | Stock | Checked |
|---|---|---|---|---|
Mwave | A$5,894 | in stock | 20 Oct 2026, 7:44 am AEST |
Community measured
No reader results yet. Be the first to submit one →
Which models fit? (8k context)
| Model | Quant | Needs / usable | Fit | Est. tok/s |
|---|---|---|---|---|
Q4_K_M | 464.4 / 48.0 GB | no | – | |
Q4_K_M | 499.4 / 48.0 GB | no | – | |
Q4_K_M | 20.0 / 48.0 GB | fits | 104 estimate | |
Q4_K_M | 348.5 / 48.0 GB | no | – | |
Q4_K_M | 15.7 / 48.0 GB | fits | 156 estimate | |
Q4_K_M | 45.9 / 48.0 GB | tight | 35 estimate | |
Q4_K_M | 22.5 / 48.0 GB | fits | 104 estimate | |
Q4_K_M | 305.3 / 48.0 GB | no | – | |
MiniCPM V 4.7 1B new | Q4_K_M | 2.0 / 48.0 GB | fits | 202 estimate |
Q4_K_M | 464.4 / 48.0 GB | no | – | |
Q4_K_M | 195.9 / 48.0 GB | no | – | |
GLM 5.3 (MoE) new | Q4_K_M | 458.4 / 48.0 GB | no | – |
Q4_K_M | 110.3 / 48.0 GB | no | – | |
Q4_K_M | 18.4 / 48.0 GB | fits | 11 estimate | |
Q4_K_M | 20.2 / 48.0 GB | fits | 104 estimate | |
Q4_K_M | 9.1 / 48.0 GB | fits | 26 estimate | |
Q4_K_M | 23.0 / 48.0 GB | fits | 104 estimate | |
Q4_K_M | 81.4 / 48.0 GB | no | – | |
Q4_K_M | 22.1 / 48.0 GB | fits | 10 estimate | |
Q4_K_M | 17.2 / 48.0 GB | fits | 82 estimate | |
Q4_K_M | 6.0 / 48.0 GB | fits | 39 estimate | |
Q4_K_M | 7.1 / 48.0 GB | fits | 32 estimate | |
Q4_K_M | 4.1 / 48.0 GB | fits | 67 estimate | |
Q4_K_M | 77.0 / 48.0 GB | no | – | |
Q4_K_M | 20.4 / 48.0 GB | fits | 104 estimate | |
gpt-oss 20B (MoE) older | MXFP4 | 12.4 / 48.0 GB | fits | 99 estimate |
gpt-oss 120B (MoE) older | MXFP4 | 63.5 / 48.0 GB | no | – |
Qwen 3 4B older | Q4_K_M | 4.6 / 48.0 GB | fits | 78 estimate |
Qwen 3 8B older | Q4_K_M | 7.2 / 48.0 GB | fits | 38 estimate |
Qwen 3 32B older | Q4_K_M | 23.0 / 48.0 GB | fits | 10 estimate |
Llama 3.1 8B Instruct older | Q4_K_M | 6.9 / 48.0 GB | fits | 39 estimate |
Mistral 7B Instruct v0.3 older | Q4_K_M | 6.5 / 48.0 GB | fits | 43 estimate |