Files and memory at 8K context
No verified quantized file for the requested formats.
Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory. Legacy model: sizes on device pages are estimated from parameter count.
Quality
Artificial Analysis Intelligence Index
Unknown
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 19
| Hardware | Quant | Backend | Prompt t/s | Gen t/s | Date | Source |
|---|---|---|---|---|---|---|
| NVIDIA DGX Spark | Q4_K_M | Ollama | 834 | 10.8 | 2025-10-23 | ollama.com |
| NVIDIA DGX Spark | Q8_0 | Ollama | 585 | 7.2 | 2025-10-23 | ollama.com |
| NVIDIA DGX Spark | Q4_K_M | Ollama | — | 11.5 | 2025-10-13 | docs.google.com |
| NVIDIA DGX Spark | Q8_0 | Ollama | — | 7.3 | 2025-10-13 | docs.google.com |
| RTX Pro 6000 Blackwell Edition | Q4_K_M | Ollama | — | 63.3 | 2025-10-13 | docs.google.com |
| RTX Pro 6000 Blackwell Edition | Q8_0 | Ollama | — | 43.4 | 2025-10-13 | docs.google.com |
| GeForce RTX 5090 | Q4_K_M | Ollama | — | 65 | 2025-10-13 | docs.google.com |
| NVIDIA RTX PRO 4500 Blackwell | Q4_K_M | llama.cpp CUDA | 1,874 | 41.8 | 2025-11-14 | llama.cpp #15013 |
| NVIDIA RTX PRO 4500 Blackwell | Q4_K_M | llama.cpp CUDA | 2,000 | 42.8 | 2025-11-14 | llama.cpp #15013 |
| NVIDIA DGX Spark | FP8 | SGLang | 717 | 3.8 | 2025-10-13 | docs.google.com |
| RTX Pro 6000 Blackwell Edition | FP8 | SGLang | 6,416 | 22.6 | 2025-10-13 | docs.google.com |
| Mac Studio M1 Max | Q4_K_M | Ollama | — | 13 | 2025-10-13 | docs.google.com |
| Mac Studio M1 Max | Q8_0 | Ollama | — | 10.1 | 2025-10-13 | docs.google.com |
| Mac Mini M4 Pro | Q4_K_M | Ollama | — | 10.6 | 2025-10-13 | docs.google.com |
| Framework Desktop (AMD Ryzen AI Max+ 395, 128GB LPDDR5x-8000, pre-production) | UD-Q4_K_XL | llama.cpp ROCm | 302 | 10.7 | 2025-08-08 | lhl/strix-halo-testing |
| Framework Desktop (AMD Ryzen AI Max+ 395, 128GB LPDDR5x-8000, pre-production) | UD-Q4_K_XL | llama.cpp Vulkan | 115 | 11.8 | 2025-08-08 | lhl/strix-halo-testing |
| AMD Radeon RX 7900 XTX | Q6_K | llama.cpp ROCm | 628 | 6.8 | 2025-05-21 | llama.cpp #10879 |
| AMD Radeon RX 7900 XTX | Q4_0 | llama.cpp Vulkan | 500 | 35.3 | 2025-05-21 | llama.cpp #10879 |
| M4 Max, 32 GPU cores (Mac Studio 2024) | Q4_0 | llama.cpp Metal | 199 | 18.7 | 2025-05-21 | llama.cpp #4167 |
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database