RTX 4070 Ti SUPER
20 records across 6 models (quants: EXL2 8.0bpw, MXFP4, PTQ1_0, Q4_0, Q4_K, Q8_0).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 4070 Ti SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 128.9 | 5628.1 | – | – | 4096 | – | sourced | – | source |
| RTX 4070 Ti SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 113.6 | 4182.7 | – | – | 16384 | – | sourced | – | source |
| RTX 4070 Ti SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 98.7 | 3020.0 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 Ti SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 78.7 | 1716.2 | – | – | 65536 | – | sourced | – | source |
| RTX 4070 Ti SUPER | gpt-oss 20B 20B | MXFP4 | llama.cpp | 57.5 | 993.5 | – | – | 131072 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Llama 3 8B Instruct 8B | EXL2 8.0bpw | ExLlamaV2 | 64 | – | – | – | 8192 | 2024-05 | community | – | source |
| RTX 4070 Ti SUPER | Llama 3 8B Instruct 8B | Q8_0 | LM Studio | 56 | – | – | – | 8192 | 2024-05 | community | – | source |
| RTX 4070 Ti SUPER | llama 7B | Q4_0 | llama.cpp (Vulkan) | 135.81 | 6801.18 | – | – | tg128 | 2025-09-24 | community | – | source |
| RTX 4070 Ti SUPER | llama 7B | Q4_0 | llama.cpp (Vulkan) | 129.45 | 6099.18 | – | – | tg128 | 2025-09-24 | community | – | source |
| RTX 4070 Ti SUPER | Qwen3 14B 14B | Q4_K | llama.cpp | 58.1 | 3048.0 | – | – | 4096 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Qwen3 14B 14B | Q4_K | llama.cpp | 47.2 | 2003.4 | – | – | 16384 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Qwen3 14B 14B | Q4_K | llama.cpp | 37.7 | 1236.9 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 96.3 | 5220.1 | – | – | 4096 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 72.2 | 3050.7 | – | – | 16384 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 54.5 | 1616.6 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 36.6 | 829.4 | – | – | 65536 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Ternary-Bonsai-2-27B | PTQ1_0 | llama.cpp (xyz-llama fork) | 156.3 | – | – | – | 163840 | 2026-09 | community | – | source |
| RTX 4070 Ti SUPER | Ternary-Bonsai-2-27B | PTQ1_0 | llama.cpp (xyz-llama fork) | 144.2 | – | – | – | 163840 | 2026-09 | community | – | source |
| RTX 4070 Ti SUPER | Ternary-Bonsai-2-27B | PTQ1_0 | llama.cpp (xyz-llama fork) | 141.3 | – | – | – | 163840 | 2026-09 | community | – | source |
| RTX 4070 Ti SUPER | Ternary-Bonsai-2-27B | PTQ1_0 | llama.cpp (xyz-llama fork) | 139.5 | – | – | – | 163840 | 2026-09 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085