RigCheck updates New and updated local AI hardware checkers https://localrigcheck.com/feed.xml 2026-10-09T00:00:00Z RigCheck Mistral Medium 3.5: The checker now gives the llama-server command for your setup, and opens prefilled from the home page finder https://localrigcheck.com/mistral-medium-3-5/#20261009-348daf9584 2026-10-09T00:00:00Z The checker now gives the llama-server command for your setup, and opens prefilled from the home page finder Qwen3.8-Flash-Next: The checker now gives the llama-server command for your setup, and opens prefilled from the home page finder https://localrigcheck.com/qwen-3-8-flash-next/#20261009-348daf9584 2026-10-09T00:00:00Z The checker now gives the llama-server command for your setup, and opens prefilled from the home page finder Strata checker: Clearer dates (page updated vs sources checked), no unexplained blanks in the tables, errors list trimmed to the common five with the upstream link https://localrigcheck.com/strata/#20261009-f407b8aa39 2026-10-09T00:00:00Z Clearer dates (page updated vs sources checked), no unexplained blanks in the tables, errors list trimmed to the common five with the upstream link Strata checker: Next step after the verdict: the install command, or Strata's community guide for experimental cards and older CPUs https://localrigcheck.com/strata/#20261009-1216d87329 2026-10-09T00:00:00Z Next step after the verdict: the install command, or Strata's community guide for experimental cards and older CPUs Mistral Large 4: Ollama lists only a cloud tag so far; Mistral's Hugging Face page gives October 31 as the weights ETA https://localrigcheck.com/mistral-large-4/#20261008-24a235bd18 2026-10-08T00:00:00Z Ollama lists only a cloud tag so far; Mistral's Hugging Face page gives October 31 as the weights ETA Mistral Large 4: 52B parameters active per token (49B without embeddings and output layers), per Mistral; le Chonk nickname explained https://localrigcheck.com/mistral-large-4/#20261008-a332d396b2 2026-10-08T00:00:00Z 52B parameters active per token (49B without embeddings and output layers), per Mistral; le Chonk nickname explained Mistral Medium 3.5: Checker launched: will the dense 128B model fit your GPU, RAM or Mac, with real GGUF sizes, layer offload and speed ceilings https://localrigcheck.com/mistral-medium-3-5/#20261008-0722bb799e 2026-10-08T00:00:00Z Checker launched: will the dense 128B model fit your GPU, RAM or Mac, with real GGUF sizes, layer offload and speed ceilings Qwen3.8-Flash-Next: Checker launched: will Qwen3.8-Flash-Next fit your RAM, GPU or Mac with llama.cpp, from real GGUF file sizes, plus the published speeds https://localrigcheck.com/qwen-3-8-flash-next/#20261008-5d230b1889 2026-10-08T00:00:00Z Checker launched: will Qwen3.8-Flash-Next fit your RAM, GPU or Mac with llama.cpp, from real GGUF file sizes, plus the published speeds Strata checker: New FAQ: Qwen has released no Qwen3.8-Flash-Next Coder; the Coder in Strata is ISTA-DASLab's code-focused cut https://localrigcheck.com/strata/#20261008-582729405c 2026-10-08T00:00:00Z New FAQ: Qwen has released no Qwen3.8-Flash-Next Coder; the Coder in Strata is ISTA-DASLab's code-focused cut Mistral Large 4: Calculator launched: memory at BF16, FP8, 4-bit and 2-bit, GPUs or Macs needed, cost next to the API https://localrigcheck.com/mistral-large-4/#20261007-52e8abc654 2026-10-07T00:00:00Z Calculator launched: memory at BF16, FP8, 4-bit and 2-bit, GPUs or Macs needed, cost next to the API Strata checker: Checker launched: GPU, RAM and disk verdict, the right model size and published speeds for your card https://localrigcheck.com/strata/#20261007-e8b7f1ca0d 2026-10-07T00:00:00Z Checker launched: GPU, RAM and disk verdict, the right model size and published speeds for your card