Ministral-3-8B-Instruct-2512 · Q3_K_S L2 Cross-framework verified NVIDIA RTX 4090 · 24GB · Ollama
Config (latest run) Windows 11 24H2 CUDA 12.8 Q3_K_S Ollama v0.42 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · IQ2_M L2 Cross-framework verified NVIDIA RTX 4090 · 24GB · Strata
Config (latest run) Windows 11 24H2 CUDA 12.8 IQ2_M Strata v0.38 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q4_K_S L2 Cross-framework verified NVIDIA RTX 3090 · 24GB · vLLM
Config (latest run) Windows 11 24H2 CUDA 12.4 Q4_K_S vLLM v0.34 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q3_K_S L2 Cross-framework verified NVIDIA RTX 3090 · 24GB · Strata
Config (latest run) Ubuntu 24.04 CUDA 12.8 Q3_K_S Strata v0.30 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q5_K_M L2 Cross-framework verified AMD Radeon RX 7900 XTX · 24GB · vLLM
Config (latest run) Ubuntu 22.04 CUDA 12.4 Q5_K_M vLLM v0.48 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · IQ3_S L2 Cross-framework verified AMD Radeon RX 7900 XTX · 24GB · Ollama
Config (latest run) Ubuntu 24.04 CUDA 12.4 IQ3_S Ollama v0.31 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · IQ1_S L2 Cross-framework verified NVIDIA RTX 5090 · 32GB · llama.cpp
Config (latest run) Ubuntu 24.04 CUDA 12.6 IQ1_S llama.cpp v0.37 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q3_K_S L2 Cross-framework verified NVIDIA RTX 5090 · 32GB · vLLM
Config (latest run) Ubuntu 22.04 CUDA 12.6 Q3_K_S vLLM v0.41 Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q4_K_S L2 Cross-framework verified NVIDIA RTX 5080 · 16GB · llama.cpp
Config (latest run) Windows 11 24H2 CUDA 12.8 Q4_K_S llama.cpp v0.31 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · IQ3_XS L2 Cross-framework verified NVIDIA RTX 4080 Super · 16GB · vLLM
Config (latest run) Ubuntu 22.04 CUDA 12.8 IQ3_XS vLLM v0.39 Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q3_K_S L2 Cross-framework verified NVIDIA RTX 4080 Super · 16GB · Ollama
Config (latest run) Windows 11 23H2 CUDA 12.8 Q3_K_S Ollama v0.21 Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q2_K L2 Cross-framework verified AMD Ryzen AI Max+ 395 · 128GB · llama.cpp
Config (latest run) Ubuntu 22.04 CUDA 12.8 Q2_K llama.cpp v0.27 Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q3_K_L L2 Cross-framework verified AMD Ryzen AI Max+ 395 · 128GB · Ollama
Config (latest run) Windows 11 23H2 CUDA 12.4 Q3_K_L Ollama v0.37 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · IQ4_XS L2 Cross-framework verified Apple M5 Max · 128GB · llama.cpp
Config (latest run) macOS 26.1 IQ4_XS llama.cpp v0.27 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · IQ4_XS L2 Cross-framework verified Apple M5 Max · 128GB · Ollama
Config (latest run) macOS 26.1 IQ4_XS Ollama v0.23 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q5_K_M L2 Cross-framework verified Apple M5 Ultra · 512GB · llama.cpp
Config (latest run) macOS 26.1 Q5_K_M llama.cpp v0.21 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q3_K_S L2 Cross-framework verified Apple M5 Ultra · 512GB · Ollama
Config (latest run) macOS 26.1 Q3_K_S Ollama v0.31 Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q8_0 L2 Cross-framework verified NVIDIA H100 80GB HBM3 · 80GB · llama.cpp
Config (latest run) Ubuntu 24.04 CUDA 13.0 Q8_0 llama.cpp v0.37 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q3_K_M L2 Cross-framework verified NVIDIA H100 80GB HBM3 · 80GB · vLLM
Config (latest run) Ubuntu 22.04 CUDA 12.8 Q3_K_M vLLM v0.29 Flash Attention Sources: Other · 1 runs · 1 independent sources
Ministral-3-8B-Instruct-2512 · Q5_K_S L2 Cross-framework verified NVIDIA H20 · 97GB · vLLM
Config (latest run) Ubuntu 24.04 CUDA 12.4 Q5_K_S vLLM v0.53 Flash Attention Sources: Other · 1 runs · 1 independent sources