NVIDIA RTX 4060 Ti (16GB)
The NVIDIA RTX 4060 Ti (16GB) features 16 GB of dedicated VRAM and 288 GB/s memory bandwidth, supporting CUDA and TensorRT-LLM runtimes for full-precision and quantized inference.
Memory
16 GB
Usable Memory Ceiling
16 GB
Bandwidth
288 GB/s
Max Inference Class
14B Models (Q4)
TDP
165W
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 NVIDIA RTX 4060 Ti (16GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX 4060 Ti (16GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 14 tok/s | ~4.0s | |
#93 | Qwen3.5-27B | 27B | INT4 | 14 tok/s | ~4.0s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 1 tok/s | ~40.0s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 20 tok/s | ~1.8s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 68 tok/s | ~660 ms | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 42 tok/s 25 tok/s | ~1.2s ~1.2s | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 15 tok/s | ~903 ms ~916 ms ~1.1s | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 23 tok/s 14 tok/s | ~1.5s ~1.8s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 28 tok/s | ~532 ms ~539 ms ~555 ms | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 29 tok/s | ~686 ms | |
#144 | GLM-4V | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~1.2s ~1.3s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 13 tok/s 8 tok/s 4 tok/s | ~3.6s ~3.7s ~3.8s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.0s | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.0s | |
#166 | Phi-4 | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~1.8s ~2.1s | |
#167 | Gemma 3 27B | 27B | INT4 | 14 tok/s | ~4.0s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 36 tok/s 25 tok/s | ~911 ms ~924 ms | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 29 tok/s 15 tok/s | ~1.8s ~2.1s | |
#183 | Ministral 3 14B | 14B | INT4 | 20 tok/s | ~1.8s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 32 tok/s 18 tok/s | ~1.5s ~1.7s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 16 tok/s | ~3.3s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 33 tok/s 22 tok/s | ~1.0s ~1.1s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 14 tok/s | ~4.0s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~1.8s ~2.1s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 67 tok/s 41 tok/s 22 tok/s | ~668 ms ~677 ms ~698 ms | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 47 tok/s 28 tok/s | ~1.0s ~1.0s | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 28 tok/s | ~532 ms ~539 ms ~555 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 63 tok/s 48 tok/s 30 tok/s | ~414 ms ~419 ms ~431 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 42 tok/s 25 tok/s | ~1.2s ~1.2s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 209 tok/s 160 tok/s 105 tok/s | ~120 ms ~121 ms ~124 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~1.8s ~2.1s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 28 tok/s | ~532 ms ~539 ms ~555 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.0s | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 53 tok/s 31 tok/s 16 tok/s | ~902 ms ~915 ms ~1.0s | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 140 tok/s 98 tok/s 58 tok/s | ~245 ms ~248 ms ~255 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.0s | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 256 tok/s 229 tok/s 183 tok/s | ~44 ms ~45 ms ~46 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 236 tok/s 187 tok/s 128 tok/s | ~90 ms ~91 ms ~94 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.0s | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 83 tok/s 53 tok/s 29 tok/s | ~507 ms ~514 ms ~529 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 15 tok/s | ~903 ms ~916 ms ~1.1s | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.0s | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 151 tok/s 107 tok/s 65 tok/s | ~217 ms ~220 ms ~226 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 98 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~426 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 83 tok/s 53 tok/s 29 tok/s | ~507 ms ~514 ms ~529 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 63 tok/s 53 tok/s 35 tok/s | ~312 ms ~315 ms ~349 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~939 ms ~953 ms ~1.1s | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 186 tok/s 139 tok/s 89 tok/s | ~150 ms ~152 ms ~156 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~1.8s ~2.1s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 36 tok/s 25 tok/s | ~911 ms ~924 ms | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 15 tok/s | ~903 ms ~916 ms ~1.1s | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 15 tok/s | ~903 ms ~916 ms ~1.1s | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 186 tok/s 139 tok/s 89 tok/s | ~150 ms ~152 ms ~156 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~939 ms ~953 ms ~1.1s | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 36 tok/s 25 tok/s | ~911 ms ~924 ms | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 137 tok/s 91 tok/s 52 tok/s | ~284 ms ~288 ms ~296 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 40 tok/s 28 tok/s 16 tok/s | ~787 ms ~797 ms ~891 ms | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 40 tok/s 28 tok/s 16 tok/s | ~787 ms ~797 ms ~891 ms | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 40 tok/s 28 tok/s 16 tok/s | ~787 ms ~797 ms ~891 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 289 tok/s 250 tok/s 191 tok/s | ~48 ms ~49 ms ~50 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 252 tok/s 204 tok/s 144 tok/s | ~76 ms ~77 ms ~79 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 252 tok/s 204 tok/s 144 tok/s | ~76 ms ~77 ms ~79 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 245 tok/s 218 tok/s 172 tok/s | ~49 ms ~49 ms ~50 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 245 tok/s 218 tok/s 172 tok/s | ~49 ms ~49 ms ~50 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 236 tok/s 187 tok/s 128 tok/s | ~90 ms ~91 ms ~94 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 234 tok/s 186 tok/s 127 tok/s | ~91 ms ~93 ms ~95 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 234 tok/s 186 tok/s 127 tok/s | ~91 ms ~93 ms ~95 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 231 tok/s 182 tok/s 124 tok/s | ~95 ms ~96 ms ~99 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 202 tok/s 153 tok/s 100 tok/s | ~129 ms ~130 ms ~134 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 202 tok/s 153 tok/s 100 tok/s | ~129 ms ~130 ms ~134 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 202 tok/s 153 tok/s 100 tok/s | ~129 ms ~130 ms ~134 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 199 tok/s 145 tok/s 91 tok/s | ~150 ms ~152 ms ~156 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 186 tok/s 139 tok/s 89 tok/s | ~150 ms ~152 ms ~156 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 186 tok/s 139 tok/s 89 tok/s | ~150 ms ~152 ms ~156 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 169 tok/s 123 tok/s 76 tok/s | ~180 ms ~182 ms ~187 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 164 tok/s 118 tok/s 72 tok/s | ~190 ms ~192 ms ~198 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 151 tok/s 107 tok/s 65 tok/s | ~217 ms ~220 ms ~226 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 151 tok/s 107 tok/s 65 tok/s | ~217 ms ~220 ms ~226 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 151 tok/s 107 tok/s 65 tok/s | ~217 ms ~220 ms ~226 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 151 tok/s 107 tok/s 65 tok/s | ~217 ms ~220 ms ~226 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 140 tok/s 98 tok/s 58 tok/s | ~245 ms ~248 ms ~255 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 140 tok/s 98 tok/s 58 tok/s | ~245 ms ~248 ms ~255 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 140 tok/s 98 tok/s 58 tok/s | ~245 ms ~248 ms ~255 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 136 tok/s 94 tok/s 55 tok/s | ~257 ms ~261 ms ~268 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 127 tok/s 87 tok/s | ~320 ms ~324 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 127 tok/s 87 tok/s 51 tok/s | ~285 ms ~289 ms ~297 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 123 tok/s 84 tok/s 49 tok/s | ~297 ms ~301 ms ~310 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 120 tok/s 81 tok/s 47 tok/s | ~310 ms ~314 ms ~323 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 116 tok/s 78 tok/s 45 tok/s | ~323 ms ~327 ms ~337 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 111 tok/s 73 tok/s 42 tok/s | ~346 ms ~351 ms ~361 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 109 tok/s 72 tok/s 41 tok/s | ~354 ms ~359 ms ~369 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 109 tok/s 72 tok/s 41 tok/s | ~354 ms ~359 ms ~369 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 105 tok/s 66 tok/s 37 tok/s | ~407 ms ~413 ms ~425 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 103 tok/s 84 tok/s 58 tok/s | ~194 ms ~196 ms ~201 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 103 tok/s 84 tok/s 58 tok/s | ~194 ms ~196 ms ~201 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 103 tok/s 84 tok/s 58 tok/s | ~194 ms ~196 ms ~201 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 100 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~425 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 100 tok/s 65 tok/s | ~398 ms ~437 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 98 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~426 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 98 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~426 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 98 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~426 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 98 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~426 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 98 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~426 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 98 tok/s 64 tok/s 36 tok/s | ~408 ms ~413 ms ~426 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 86 tok/s | ~489 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 80 tok/s | ~540 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 80 tok/s | ~540 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 28 tok/s | ~532 ms ~539 ms ~555 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 28 tok/s | ~532 ms ~539 ms ~555 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 28 tok/s | ~532 ms ~539 ms ~555 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 28 tok/s | ~532 ms ~539 ms ~555 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 76 tok/s 61 tok/s 41 tok/s | ~290 ms ~294 ms ~302 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 73 tok/s | ~613 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 73 tok/s | ~613 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 68 tok/s 42 tok/s 22 tok/s | ~655 ms ~665 ms ~685 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 68 tok/s 42 tok/s 22 tok/s | ~655 ms ~665 ms ~685 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 68 tok/s 42 tok/s 22 tok/s | ~655 ms ~665 ms ~685 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 66 tok/s 51 tok/s 33 tok/s | ~377 ms ~381 ms ~392 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 63 tok/s 48 tok/s 30 tok/s | ~414 ms ~419 ms ~431 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 63 tok/s 48 tok/s 30 tok/s | ~414 ms ~419 ms ~431 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 54 tok/s 32 tok/s 16 tok/s | ~902 ms ~915 ms ~1.0s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 53 tok/s 32 tok/s 16 tok/s | ~878 ms ~891 ms ~996 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 53 tok/s 32 tok/s 16 tok/s | ~878 ms ~891 ms ~996 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 15 tok/s | ~903 ms ~916 ms ~1.1s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 51 tok/s 31 tok/s 15 tok/s | ~903 ms ~916 ms ~1.1s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~939 ms ~953 ms ~1.1s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 47 tok/s 28 tok/s | ~1.0s ~1.0s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.1s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.0s ~1.1s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 42 tok/s 25 tok/s | ~1.2s ~1.2s | |
- | LensVLM 9B | 9B | INT4 Q8 | 42 tok/s 25 tok/s | ~1.2s ~1.2s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 42 tok/s 25 tok/s | ~1.2s ~1.2s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 40 tok/s 28 tok/s 16 tok/s | ~787 ms ~797 ms ~891 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 40 tok/s 28 tok/s 16 tok/s | ~787 ms ~797 ms ~891 ms | |
- | Falcon3-10B | 10B | INT4 Q8 | 38 tok/s 22 tok/s | ~1.3s ~1.3s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 38 tok/s 22 tok/s | ~1.3s ~1.3s | |
- | Falcon2-11B | 11B | INT4 Q8 | 36 tok/s 21 tok/s | ~1.4s ~1.4s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 36 tok/s 25 tok/s | ~911 ms ~924 ms | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 | 36 tok/s | ~533 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 36 tok/s 25 tok/s | ~911 ms ~924 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 36 tok/s 25 tok/s | ~923 ms ~936 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 36 tok/s 25 tok/s | ~923 ms ~936 ms | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 33 tok/s 22 tok/s | ~1.0s ~1.1s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 33 tok/s 22 tok/s | ~1.0s ~1.1s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~1.5s ~1.7s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~1.5s ~1.7s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~1.5s ~1.7s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~1.5s ~1.7s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 32 tok/s 18 tok/s | ~1.5s ~1.7s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 30 tok/s 17 tok/s | ~1.7s ~1.8s | |
- | GLM-4-9B | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~1.2s ~1.3s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~1.2s ~1.3s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~1.2s ~1.3s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 29 tok/s 19 tok/s | ~1.2s ~1.3s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 29 tok/s 19 tok/s | ~1.2s ~1.3s | |
- | Yi-9B | 9B | INT4 Q8 | 29 tok/s 19 tok/s | ~1.2s ~1.3s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~1.8s ~2.1s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~1.8s ~2.1s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 28 tok/s 15 tok/s | ~1.8s ~2.1s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 26 tok/s 14 tok/s | ~1.9s ~2.3s | |
- | GreenMind-14B-R1 | 14B | INT4 | 20 tok/s | ~1.8s | |
- | Arete 27B | 27B | INT4 | 14 tok/s | ~4.0s | |
- | AREX-2 | 27B | INT4 | 14 tok/s | ~4.0s | |
- | PPLX Decider v1 27B | 27B | INT4 | 14 tok/s | ~4.0s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 14 tok/s | ~4.0s | |
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 NVIDIA RTX 4060 Ti (16GB).
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 288 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 64 tok/s on an 8B Q4 model and 8 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning