Intel · workstation
Arc Pro A60 12GB
Arc Pro A60 12GB has 12 GB of VRAM at 384 GB/s — about 11.16 GiB usable after driver and compositor overhead. 1390 of 2118 indexed models fit at 128K context with q4_0 KV.
Spec sheet· bandwidth, theoreticalFrom the file· fit from summed bytesPredicted· speed
Memory
12 GB
GDDR6
Bandwidth
384 GB/s
192-bit bus
Tensor FP16
—
dense
TDP
130 W
video 14text 1172vision language 118embedding 26audio tts 21image 1audio asr 38
What fits at 128K context
largest quantization that fits, per model · 1390 of 2118 indexed
| Model | Best quant | Params | Weights● | KV● | Total in memory◐ | Headroom◐ | tok/s◐ |
|---|---|---|---|---|---|---|---|
| Wan2.1-FLF2V-14B-720P | Q4_1 | 16.4B | 10.32 GiB | 0.00 GiB | 11.16 GiB | 0.00 GiB | 20±30% |
| Qwen3-16B-A3BMoE | IQ3_M | 16.0B | 6.99 GiB | 3.38 GiB | 11.16 GiB | 0.00 GiB | 25±37% |
| ERNIE-21B-A3B-Thinking-Gemini-3-Pro-High-Reasoning-V2 | I1-IQ3_XS | 21.8B | 8.37 GiB | 1.97 GiB | 11.16 GiB | 0.00 GiB | 20±30% |
| ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking | I1-IQ3_XS | 21.8B | 8.37 GiB | 1.97 GiB | 11.16 GiB | 0.00 GiB | 20±30% |
| ERNIE-4.5-21B-A3B-Thinking | I1-IQ3_XS | 21.8B | 8.37 GiB | 1.97 GiB | 11.16 GiB | 0.00 GiB | 20±30% |
| Wan2.1-I2V-14B-480P | Q4_1 | 16.4B | 10.32 GiB | 0.00 GiB | 11.15 GiB | 0.01 GiB | 20±30% |
| Wan2.1-I2V-14B-720P | Q4_1 | 16.4B | 10.32 GiB | 0.00 GiB | 11.15 GiB | 0.01 GiB | 20±30% |
| LFM2-24B-A2BMoE | Q3_K_S | 23.8B | 9.64 GiB | 0.70 GiB | 11.15 GiB | 0.01 GiB | 58±37% |
| AceReason-Nemotron-14B | UD-IQ1_S | 14.8B | 3.55 GiB | 6.75 GiB | 11.15 GiB | 0.01 GiB | 20±30% |
| OpenCaption-2B-VL-SFT-v1.0 | F32 | 2.1B | 6.42 GiB | 3.94 GiB | 11.15 GiB | 0.01 GiB | 20±30% |
| Smilodon-9B-v1 | I1-IQ3_M | 10.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| bella-bartender-v2 | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| Gemma-The-Writer-9B-HERETIC-Uncensored-Abliterated | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| Dirty-Muse-Writer-v01-Uncensored-Erotica-NSFW | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| Gemma-2-9B-It-SPPO-Iter3 | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| Gemma-SEA-LION-v3-9B-IT | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| G2-Darkest-Writer-Dirty-Shirley-9B-v2 | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| G2-Darkest-Writer-9B-v1 | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| Tiger-Gemma-9B-v3 | I1-IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| gemma-2-9b-it-abliterated | IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| gemma-2-9b-it | IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| Tiger-Gemma-9B-v1 | IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| magnum-v4-9b | IQ3_M | 9.2B | 4.19 GiB | 6.11 GiB | 11.14 GiB | 0.02 GiB | 20±30% |
| Ling-mini-2.0MoE | Q4_K_S | 16.3B | 8.94 GiB | 1.41 GiB | 11.14 GiB | 0.02 GiB | 50±37% |
| Ministral-3-8B-Instruct-2512-BF16-abliterated | I1-Q5_K_S | 8.9B | 5.51 GiB | 4.78 GiB | 11.13 GiB | 0.03 GiB | 20±30% |
| Ministral-3-8B-Instruct-2512-BF16 | Q5_K_S | 8.9B | 5.51 GiB | 4.78 GiB | 11.13 GiB | 0.03 GiB | 20±30% |
| Amaretto-8B | I1-Q5_K_S | 8.9B | 5.51 GiB | 4.78 GiB | 11.13 GiB | 0.03 GiB | 20±30% |
| Ministral-3-8B-Instruct-2512 | Q5_K_S | 8.9B | 5.51 GiB | 4.78 GiB | 11.13 GiB | 0.03 GiB | 20±30% |
| Ministral-3-8B-Reasoning-2512 | Q5_K_S | 8.9B | 5.51 GiB | 4.78 GiB | 11.13 GiB | 0.03 GiB | 20±30% |
| Qwen3.5-9B-GLM5.1-Distill-v1 | Q4_K_M | 9.7B | 9.16 GiB | 1.13 GiB | 11.12 GiB | 0.04 GiB | 20±30% |
| NousCoder-14B | IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| spoomplesmaxx-mini-14B | I1-IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| vanilla-cn-roleplay-0.2 | I1-IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Claria-14b | I1-IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| NTX-2.1-Pro | I1-IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Qwen3-14B-Uncensored | I1-IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| FrogMini-14B-2510 | I1-IQ2_S | — | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Qwen3-14B-abliterated | IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Josiefied-Qwen3-14B-abliterated-v3 | IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Hermes-4-14B | IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Slava-Qwen3-14B-Serbian | I1-IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Huihui-Qwen3-14B-abliterated-v2 | I1-IQ2_S | 14.8B | 4.62 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| granite-3.3-8b-instruct | Q4_K_L | 8.2B | 4.65 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| granite-3.2-8b-instruct | Q4_K_L | 8.2B | 4.65 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| granite-3.1-8b-instruct | Q4_K_L | 8.2B | 4.65 GiB | 5.63 GiB | 11.11 GiB | 0.05 GiB | 20±30% |
| Wan2.2-Distill-Models | Q5_1 | 14.3B | 10.27 GiB | 0.00 GiB | 11.10 GiB | 0.06 GiB | 20±30% |
| Bernini-R | Q5_1 | 14.3B | 10.26 GiB | 0.00 GiB | 11.10 GiB | 0.06 GiB | 20±30% |
| SkyReels-V2-DF-14B-540P | Q5_1 | 14.3B | 10.27 GiB | 0.00 GiB | 11.10 GiB | 0.06 GiB | 20±30% |
| granite-4.0-h-smallMoE | IQ2_M | 32.2B | 9.75 GiB | 0.56 GiB | 11.10 GiB | 0.06 GiB | 46±37% |
| Anubis-Mini-8B-v1 | Q5_K_L | 8.0B | 5.76 GiB | 4.50 GiB | 11.10 GiB | 0.06 GiB | 20±30% |
| gemma-3-12b-it-vl-Gemini-3-Pro-Preview-Heretic-Uncensored-Thinking | I1-Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking | I1-Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| gemma-3-12b-it-ultra-uncensored-heretic | Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| gemma-3-12b-it-vl-GLM-4.7-Flash-Heretic-Uncensored-Thinking | I1-Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| Floppa-12B-Gemma3-Uncensored | I1-Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| gemma-3-12b-it-heretic | I1-Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| gemma-3-12b-it-abliterated | Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| gemma-3-12b-it-abliterated-v2 | Q5_K_M | 11.8B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| gemma-3-12b-it | Q5_K_M | 12.2B | 7.87 GiB | 2.38 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
| Tess-4-9B | Q8_0 | 9.7B | 9.13 GiB | 1.13 GiB | 11.09 GiB | 0.07 GiB | 20±30% |
Speed is modeled, not measured: decode is memory-bandwidth bound, so tokens per second is bytes read per token against achievable bandwidth. Mixture-of-experts models carry a wider band because only the routed experts are read each step, and few have been measured publicly.
Questions people ask
- What AI models can a Arc Pro A60 12GB run?
- 1390 of 2118 indexed open-weight models fit a Arc Pro A60 12GB at 131,072 context with q4_0 KV cache, the largest being Wan2.1-FLF2V-14B-720P at Q4_1. That covers text, vision-language, image, video and speech models.
- How much usable memory does a Arc Pro A60 12GB actually have?
- Its nameplate is 12 GB, but about 11.16 GiB is available to a model once driver and compositor overhead is accounted for.
- Is a Arc Pro A60 12GB fast for local AI?
- Its memory bandwidth is 384 GB/s, and that figure — not teraflops — is what governs token generation speed. Capacity decides what you can run; bandwidth decides how fast it runs.