jonpark0/SmolLM2-135M-Instruct-krafla
Text Generation • Updated
Krafla
Q4_0, Q8_0 and mixed files for Krafla, CPU inference in C11 from SSE2 to AVX-512 and ARMv7 NEON to SVE.
Note Krafla 0.8.0+ · --chat smollm · Q4_0 72 MiB
jonpark0/SmolLM2-360M-Instruct-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat smollm · Q4_0 194 MiB
jonpark0/Qwen2.5-0.5B-Instruct-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat qwen · Q4_0 265 MiB
jonpark0/Qwen3-0.6B-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat chatml · Q4_0 320 MiB
jonpark0/Qwen3.5-0.8B-krafla
Text Generation • UpdatedNote Krafla 0.9.0+ · --chat qwen3.5-nothink · Q4_0 406 MiB
jonpark0/TinyLlama-1.1B-Chat-v1.0-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat zephyr · Q4_0 590 MiB
jonpark0/Qwen2.5-1.5B-Instruct-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat qwen · Q4_0 829 MiB
jonpark0/Qwen3-1.7B-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat chatml · Q4_0 923 MiB
jonpark0/Qwen3.5-2B-krafla
Text Generation • UpdatedNote Krafla 0.9.0+ · --chat qwen3.5-nothink · Q4_0 1012 MiB
jonpark0/SmolLM3-3B-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat chatml · Q4_0 1.6 GiB
jonpark0/Qwen3-4B-Instruct-2507-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat chatml · Q4_0 2.1 GiB
jonpark0/Qwen3.5-4B-krafla
Text Generation • UpdatedNote Krafla 0.9.0+ · --chat qwen3.5-nothink · Q4_0 2.2 GiB
jonpark0/Qwen2.5-7B-Instruct-krafla
Text Generation • UpdatedNote Krafla 0.8.0+ · --chat qwen · Q4_0 4.0 GiB
jonpark0/Qwen3-8B-krafla
Text Generation • UpdatedNote Krafla 0.9.0+ · --chat chatml · Q4_0 4.3 GiB
jonpark0/Qwen3.5-9B-krafla
Text Generation • UpdatedNote Krafla 0.9.0+ · --chat qwen3.5-nothink · Q4_0 4.7 GiB