Gemma on Intel Battlemage
Can I run Gemma 3 27B on an Arc B580?
Not at Q4_K_M — it needs 17.5 GB against 10.5 GB available. You would need 2 of these cards.
Won't fit
17.5 GB of 10.5 GB · 167%018 GB
Weights
15.6 GB
KV cache
1.1 GB
Runtime overhead
0.8 GB
Over the limit
7.0 GB
Short by 7.0 GB. You can run it with 34 of 62 layers on the Arc B580 and the rest in system RAM, at roughly 3.75 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation3.75tok/s
Prompt processing353tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of Gemma 3 27B on a Arc B580
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 | 51.0 GB | 53.0 GB | Won't fit | — | 0.73 |
| INT8 / W8A8 | 8.50 | 26.8 GB | 28.7 GB | Won't fit | — | 1.60 |
| Q8_0 (GGUF) | 8.50 | 26.8 GB | 28.7 GB | Won't fit | — | 1.60 |
| FP8 (E4M3) | 8.00 | 25.5 GB | 27.4 GB | Won't fit | — | 1.71 |
| Q6_K | 6.56 | 20.9 GB | 22.9 GB | Won't fit | — | 2.29 |
| Q5_K_M | 5.67 | 18.1 GB | 20.0 GB | Won't fit | — | 2.88 |
| Q5_K_S | 5.52 | 17.6 GB | 19.5 GB | Won't fit | — | 3.02 |
| Q4_K_M | 4.85 | 15.6 GB | 17.5 GB | Won't fit | — | 3.75 |
| AWQ 4-bit | 4.25 | 15.5 GB | 17.4 GB | Won't fit | — | 3.77 |
| GPTQ 4-bit | 4.25 | 15.5 GB | 17.4 GB | Won't fit | — | 3.77 |
| MXFP4 | 4.25 | 15.5 GB | 17.4 GB | Won't fit | — | 3.77 |
| Q4_K_S | 4.58 | 14.8 GB | 16.7 GB | Won't fit | — | 4.06 |
| Q4_0 | 4.55 | 14.7 GB | 16.6 GB | Won't fit | — | 4.19 |
| IQ4_XS | 4.25 | 13.8 GB | 15.7 GB | Won't fit | — | 4.72 |
| Q3_K_M | 3.91 | 12.7 GB | 14.7 GB | Won't fit | — | 5.57 |
| IQ3_M | 3.70 | 12.1 GB | 14.0 GB | Won't fit | — | 6.24 |
| IQ3_XXS | 3.06 | 10.2 GB | 12.1 GB | Won't fit | — | 10.6 |
| Q2_K | 2.63 | 8.9 GB | 10.8 GB | Won't fit | 4K | 18.5 |
| IQ2_XXS | 2.06 | 7.1 GB | 9.1 GB | Runs comfortably | 24K | 29.1 |
| IQ1_M | 1.75 | 6.2 GB | 8.1 GB | Runs comfortably | 35K | 33.0 |