inferencerlabs/Ling-2.6-MLX-3.6bit-INF

See Ling-2.6-1T in action - demonstration videos

Tested with an M3 Ultra 512 GiB using Inferencer app v1.11.2

• Text inference: ~11.3 tokens/s @ 1000 tokens ~431 GiB (debug build)

Q3.6-INF uses the data-agnostic INF method tuned to yield maximum general accuracy within a 512 GiB memory budget

The perplexity of this quantization has not been directly compared against the base model due to resource and time constraints. For general guidance, the evaluations below reference a similarly sized model (Kimi K2.6). However, please note that Kimi K2.6 uses quantization-aware training (QAT), so these results are not directly comparable and should be treated as context only.

Quantization (bpw)	Perplexity	Token Accuracy	Missed Divergence
Q3.5	1.1328125	94.92%	42.71%
Q3.5-INF	1.078125	96.67%	22.04%
Q3.6	1.1484375	94.72%	48.72%
Q4.2-INF	1.0546875	99.02%	13.73%
Base	Untested	100%	0.000%

• Perplexity: Measures the confidence for predicting base tokens (lower is better)
• Token Accuracy: The percentage of correctly generated base tokens
• Missed Divergence: Measures severity of misses; how much the token was missed by

Quantized with a modified version of MLX

For more details see our demonstration videos or visit Ling-2.6-1T.

Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.