Arc B580 (12GB)
The Arc B580 (12GB) provides 12 GB of memory with 456 GB/s bandwidth, supporting local inference via ROCm and Vulkan acceleration.
Memory
12 GB
Usable Memory Ceiling
12 GB
Bandwidth
456 GB/s
Max Inference Class
14B Models (Q4)
TDP
190W
VRAM Scaling by Context Length
Estimated memory requirements as context length increases. Curves crossing above the reference line indicate Out of Memory (OOM).
Precision:
Best Models to Run on Arc B580 (12GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on Arc B580 (12GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 28 tok/s | ~6.6s | |
#124 | Qwen3.5-9B | 9B | INT4 Q8 | 62 tok/s 36 tok/s | ~3.6s ~4.0s | |
#129 | K2 Horizon 7B | 7B | INT4 Q8 | 75 tok/s 47 tok/s | ~2.8s ~2.9s | |
#136 | Gemma 4 12B | 11.95B | INT4 | 34 tok/s | ~5.2s | |
#141 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~1.7s ~1.7s ~1.7s | |
#146 | GLM-4V | 9B | INT4 | 45 tok/s | ~3.6s | |
#151 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 20 tok/s 12 tok/s 6 tok/s | ~11.5s ~11.5s ~12.6s | |
#159 | Granite 4.2 8B | 8B | INT4 Q8 | 68 tok/s 39 tok/s | ~3.2s ~3.5s | |
#160 | Gemma 4 E4B | 8B | INT4 Q8 | 68 tok/s 39 tok/s | ~3.2s ~3.5s | |
#167 | Phi-4 | 14B | INT4 | 42 tok/s | ~5.6s | |
#179 | DeepSeek-R1 14B | 14B | INT4 | 44 tok/s | ~5.6s | |
#180 | OLMo 3 7B Think | 7B | INT4 Q8 | 54 tok/s 36 tok/s | ~2.9s ~3.1s | |
#184 | Ministral 3 14B | 14B | INT4 | 28 tok/s | ~6.6s | |
#187 | Gemma 3 12B | 12B | INT4 | 48 tok/s | ~4.8s | |
#190 | Ministral 3 8B | 8B | INT4 Q8 | 49 tok/s 31 tok/s | ~3.2s ~3.8s | |
#192 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
#193 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
#195 | Qwen2.5-14B | 14B | INT4 | 42 tok/s | ~5.6s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 30 tok/s | ~2.1s ~2.1s ~2.5s | |
#203 | DeepSeek-R1 8B | 8B | INT4 Q8 | 70 tok/s 42 tok/s | ~3.2s ~3.2s | |
#205 | Qwen3-4B | 4B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~1.7s ~1.7s ~1.7s | |
#206 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 91 tok/s 70 tok/s 45 tok/s | ~1.3s ~1.3s ~1.3s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 249 tok/s 202 tok/s 143 tok/s | ~362 ms ~363 ms ~365 ms | |
#209 | Gemma 2 9B | 9B | INT4 Q8 | 62 tok/s 36 tok/s | ~3.6s ~4.0s | |
#210 | Qwen3-14B | 14B | INT4 | 42 tok/s | ~5.6s | |
#211 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~1.7s ~1.7s ~1.7s | |
#212 | Qwen3-8B | 8B | INT4 Q8 | 68 tok/s 39 tok/s | ~3.2s ~3.5s | |
#214 | DeepSeek-R1 7B | 7B | INT4 Q8 | 77 tok/s 47 tok/s | ~2.8s ~2.9s | |
#215 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 182 tok/s 134 tok/s 84 tok/s | ~759 ms ~761 ms ~765 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 289 tok/s 267 tok/s 225 tok/s | ~123 ms ~123 ms ~123 ms | |
#217 | Llama 3.1 8B | 8B | INT4 Q8 | 68 tok/s 39 tok/s | ~3.2s ~3.5s | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 272 tok/s 229 tok/s 169 tok/s | ~269 ms ~270 ms ~271 ms | |
#220 | Llama 3 8B | 8B | INT4 Q8 | 68 tok/s 39 tok/s | ~3.2s ~3.5s | |
#222 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 116 tok/s 77 tok/s 44 tok/s | ~1.6s ~1.6s ~1.6s | |
#224 | Qwen2.5-7B | 7B | INT4 Q8 | 75 tok/s 47 tok/s | ~2.8s ~2.9s | |
#225 | Ministral-8B-2410 | 8B | INT4 Q8 | 68 tok/s 39 tok/s | ~3.2s ~3.5s | |
#226 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 193 tok/s 145 tok/s 93 tok/s | ~672 ms ~673 ms ~677 ms | |
#227 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
#229 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 116 tok/s 77 tok/s 44 tok/s | ~1.6s ~1.6s ~1.6s | |
#230 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 | 90 tok/s 77 tok/s | ~952 ms ~953 ms | |
#231 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 | 73 tok/s 45 tok/s | ~3.0s ~3.0s | |
#232 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 228 tok/s 181 tok/s 123 tok/s | ~460 ms ~461 ms ~464 ms | |
#233 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
#234 | Phi-3-medium | 14B | INT4 | 42 tok/s | ~5.6s | |
#235 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 54 tok/s 36 tok/s | ~2.9s ~3.1s | |
#237 | Qwen2-7B | 7B | INT4 Q8 | 75 tok/s 47 tok/s | ~2.8s ~2.9s | |
#238 | Phi-3-small | 7B | INT4 Q8 | 75 tok/s 47 tok/s | ~2.8s ~2.9s | |
#239 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 228 tok/s 181 tok/s 123 tok/s | ~460 ms ~461 ms ~464 ms | |
#240 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 | 73 tok/s 45 tok/s | ~3.0s ~3.0s | |
#242 | Gemma 1 7B | 7B | INT4 Q8 | 54 tok/s 36 tok/s | ~2.9s ~3.1s | |
#243 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 178 tok/s 126 tok/s 76 tok/s | ~886 ms ~889 ms ~894 ms | |
#244 | ChatGLM3-6B | 6B | INT4 Q8 | 60 tok/s 43 tok/s | ~2.5s ~2.5s | |
#245 | ChatGLM2-6B | 6B | INT4 Q8 | 60 tok/s 43 tok/s | ~2.5s ~2.5s | |
#246 | ChatGLM-6B | 6B | INT4 Q8 | 60 tok/s 43 tok/s | ~2.5s ~2.5s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 315 tok/s 284 tok/s 233 tok/s | ~136 ms ~136 ms ~137 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 285 tok/s 245 tok/s 186 tok/s | ~224 ms ~224 ms ~225 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 285 tok/s 245 tok/s 186 tok/s | ~224 ms ~224 ms ~225 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 280 tok/s 257 tok/s 215 tok/s | ~136 ms ~136 ms ~137 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 280 tok/s 257 tok/s 215 tok/s | ~136 ms ~136 ms ~137 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 272 tok/s 229 tok/s 169 tok/s | ~269 ms ~270 ms ~271 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 271 tok/s 227 tok/s 168 tok/s | ~273 ms ~274 ms ~275 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 271 tok/s 227 tok/s 168 tok/s | ~273 ms ~274 ms ~275 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 268 tok/s 224 tok/s 164 tok/s | ~284 ms ~284 ms ~286 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 242 tok/s 195 tok/s 136 tok/s | ~391 ms ~392 ms ~394 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 242 tok/s 195 tok/s 136 tok/s | ~391 ms ~392 ms ~394 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 242 tok/s 195 tok/s 136 tok/s | ~391 ms ~392 ms ~394 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 240 tok/s 187 tok/s 126 tok/s | ~460 ms ~461 ms ~463 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 228 tok/s 181 tok/s 123 tok/s | ~460 ms ~461 ms ~464 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 228 tok/s 181 tok/s 123 tok/s | ~460 ms ~461 ms ~464 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 211 tok/s 163 tok/s 108 tok/s | ~553 ms ~555 ms ~558 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 206 tok/s 157 tok/s 103 tok/s | ~585 ms ~587 ms ~590 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 193 tok/s 145 tok/s 93 tok/s | ~672 ms ~673 ms ~677 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 193 tok/s 145 tok/s 93 tok/s | ~672 ms ~673 ms ~677 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 193 tok/s 145 tok/s 93 tok/s | ~672 ms ~673 ms ~677 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 193 tok/s 145 tok/s 93 tok/s | ~672 ms ~673 ms ~677 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 182 tok/s 134 tok/s 84 tok/s | ~759 ms ~761 ms ~765 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 182 tok/s 134 tok/s 84 tok/s | ~759 ms ~761 ms ~765 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 182 tok/s 134 tok/s 84 tok/s | ~759 ms ~761 ms ~765 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 177 tok/s 129 tok/s 81 tok/s | ~799 ms ~801 ms ~806 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 168 tok/s 115 tok/s | ~999 ms ~1.1s | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 167 tok/s 121 tok/s 74 tok/s | ~887 ms ~889 ms ~894 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 163 tok/s 117 tok/s 72 tok/s | ~926 ms ~928 ms ~934 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 160 tok/s 113 tok/s 69 tok/s | ~965 ms ~967 ms ~973 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 156 tok/s 110 tok/s 66 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 149 tok/s 104 tok/s 62 tok/s | ~1.1s ~1.1s ~1.1s | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 147 tok/s 102 tok/s 61 tok/s | ~1.1s ~1.1s ~1.1s | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 147 tok/s 102 tok/s 61 tok/s | ~1.1s ~1.1s ~1.1s | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 142 tok/s 95 tok/s 55 tok/s | ~1.3s ~1.3s ~1.3s | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 140 tok/s 118 tok/s 85 tok/s | ~588 ms ~589 ms ~592 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 140 tok/s 118 tok/s 85 tok/s | ~588 ms ~589 ms ~592 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 140 tok/s 118 tok/s 85 tok/s | ~588 ms ~589 ms ~592 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 | 137 tok/s | ~1.2s | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 136 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~1.3s ~1.3s ~1.3s | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~1.7s ~1.7s ~1.7s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~1.7s ~1.7s ~1.7s | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~1.7s ~1.7s ~1.7s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~1.7s ~1.7s ~1.7s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 108 tok/s 88 tok/s 61 tok/s | ~890 ms ~892 ms ~897 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 97 tok/s 62 tok/s 33 tok/s | ~2.1s ~2.1s ~2.3s | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 97 tok/s 62 tok/s 33 tok/s | ~2.1s ~2.1s ~2.3s | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 97 tok/s 62 tok/s 33 tok/s | ~2.1s ~2.1s ~2.3s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 95 tok/s 75 tok/s 49 tok/s | ~1.2s ~1.2s ~1.2s | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 91 tok/s 70 tok/s 45 tok/s | ~1.3s ~1.3s ~1.3s | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 91 tok/s 70 tok/s 45 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Falcon-7B | 7B | INT4 Q8 | 79 tok/s 48 tok/s | ~2.8s ~2.9s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 | 77 tok/s 48 tok/s | ~2.8s ~2.8s | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 | 77 tok/s 48 tok/s | ~2.8s ~2.8s | |
- | Falcon3-7B | 7B | INT4 Q8 | 75 tok/s 47 tok/s | ~2.8s ~2.9s | |
- | Hy-MT2 7B | 7B | INT4 Q8 | 75 tok/s 47 tok/s | ~2.8s ~2.9s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 | 73 tok/s 45 tok/s | ~3.0s ~3.0s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 70 tok/s 42 tok/s | ~3.2s ~3.2s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 67 tok/s 39 tok/s | ~3.3s ~3.6s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 67 tok/s 39 tok/s | ~3.3s ~3.6s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 62 tok/s 36 tok/s | ~3.6s ~4.0s | |
- | LensVLM 9B | 9B | INT4 Q8 | 62 tok/s 36 tok/s | ~3.6s ~4.0s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 62 tok/s 36 tok/s | ~3.6s ~4.0s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 | 60 tok/s 43 tok/s | ~2.5s ~2.5s | |
- | Yi-6B | 6B | INT4 Q8 | 60 tok/s 43 tok/s | ~2.5s ~2.5s | |
- | Falcon3-10B | 10B | INT4 Q8 | 57 tok/s 31 tok/s | ~4.0s ~4.7s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 57 tok/s 31 tok/s | ~4.0s ~4.7s | |
- | Falcon2-11B | 11B | INT4 Q8 | 54 tok/s 29 tok/s | ~4.4s ~5.2s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 54 tok/s 36 tok/s | ~2.9s ~3.1s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 54 tok/s 36 tok/s | ~2.9s ~3.1s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 53 tok/s 36 tok/s | ~2.9s ~3.1s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 53 tok/s 36 tok/s | ~2.9s ~3.1s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 | 49 tok/s | ~4.8s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 | 49 tok/s | ~4.8s | |
- | FLUX.1 Dev | 11.9B | INT4 | 49 tok/s | ~4.8s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 | 49 tok/s | ~4.8s | |
- | FLUX.1 Schnell | 11.9B | INT4 | 49 tok/s | ~4.8s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 49 tok/s 31 tok/s | ~3.2s ~3.8s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 49 tok/s 31 tok/s | ~3.2s ~3.8s | |
- | GLM-4-9B | 9B | INT4 | 45 tok/s | ~3.6s | |
- | GLM-4-9B-Chat | 9B | INT4 | 45 tok/s | ~3.6s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 | 45 tok/s | ~3.6s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 | 45 tok/s | ~5.2s | |
- | Yi-9B | 9B | INT4 | 45 tok/s | ~3.6s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 | 44 tok/s | ~3.7s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 | 44 tok/s | ~3.7s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 | 42 tok/s | ~5.6s | |
- | Wan 2.1 T2V 14B | 14B | INT4 | 42 tok/s | ~5.6s | |
- | Wan 2.2 T2V A14B | 14B | INT4 | 42 tok/s | ~5.6s | |
- | FLUX.2 Dev | 15B | INT4 | 40 tok/s | ~6.0s | |
- | GreenMind-14B-R1 | 14B | INT4 | 28 tok/s | ~6.6s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
14B Models
8-bit
8B Models
16-bit
3B Models
Fine-Tuning Capacity
Hardware capacity for local training and adapter fine-tuning.
Context Length:
QLoRA
14B Models
LoRA
8B Models
Full Parameter Training
1B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on Arc B580 (12GB).
Inference Sweet Spot
Optimal for 8B models across extended context (32k+). 14B models fit comfortably at Q4 precision with standard context.
Bandwidth & Speed Profile
With 456 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 101 tok/s on an 8B Q4 model and 12 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning