Melvin56/kanana-nano-2.1b-instruct-GGUF

Original Model : kakaocorp/kanana-nano-2.1b-instruct

All quants are made using the imatrix dataset.

Model	Size (GB)
Q2_K_S	0.91
Q2_K	0.93
Q3_K_M	1.14
Q4_K_M	1.39
Q5_K_M	1.57
Q6_K	1.83
Q8_0	2.22

	CPU (AVX2)	CPU (ARM NEON)	Metal	cuBLAS	rocBLAS	SYCL	CLBlast	Vulkan	Kompute
K-quants	✅	✅	✅	✅	✅	✅	✅ 🐢5	✅ 🐢5	❌
I-quants	✅ 🐢4	✅ 🐢4	✅ 🐢4	✅	✅	Partial¹	❌	❌	❌

✅: feature works
🚫: feature does not work
❓: unknown, please contribute if you can test it youself
🐢: feature is slow
¹: IQ3_S and IQ1_S, see #5886
²: Only with -ngl 0
³: Inference is 50% slower
⁴: Slower than K-quants of comparable size
⁵: Slower than cuBLAS/rocBLAS on similar cards
⁶: Only q8_0 and iq4_nl