09/22/26: Added 3.5, 2.5, and 2.0 BPW quants using
ed's bpw-size PR
. The FFNs are the primarily quantized feature, rest of the model remains in Q8_0 / Q6_K
This repo contains specialized MoE-quants for XiaomiMiMo/MiMo-V2.6-Flash-RL. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.
The MXFP4 quant is the "full quality" version, as the model has MXFP4 experts.
Quant
Size
Mixture
PPL
1-(Mean PPL(Q)/PPL(base))
KLD
MXFP4
162.89 GiB (4.52 BPW)
BF16 / MXFP4
5.149210 ± 0.030596
+0.0715%
-0.000000 ± 0.000000
Q3_K
137.75 GiB (3.82 BPW)
Q8_0 / Q3_K / Q3_K / MXFP4
5.177623 ± 0.030900
+0.6237%
0.123607 ± 0.000648
BPW3.5
126.19 GiB (3.50 BPW)
Q8_0 / varies
5.232510 ± 0.031063
+1.6904%
0.138808 ± 0.000718
IQ2_S
106.31 GiB (2.95 BPW)
Q6_K / IQ2_S / IQ2_S / Q3_K
5.404774 ± 0.032158
+5.0382%
0.178092 ± 0.000878
BPW2.5
90.14 GiB (2.50 BPW)
Q8_0 / varies
5.739578 ± 0.034587
+11.5449%
0.243713 ± 0.001158
BPW2.0
66.99 GiB (1.86 BPW)
Q6_K / varies
7.290888 ± 0.046722
+41.6936%
0.477636 ± 0.002111
Runs of AesSedai MiMo-V2.6-Flash-RL-GGUF on huggingface.co
2.8K
Total runs
0
24-hour runs
144
3-day runs
950
7-day runs
950
30-day runs
More Information About MiMo-V2.6-Flash-RL-GGUF huggingface.co Model
MiMo-V2.6-Flash-RL-GGUF huggingface.co
MiMo-V2.6-Flash-RL-GGUF huggingface.co is an AI model on huggingface.co that provides MiMo-V2.6-Flash-RL-GGUF's model effect (), which can be used instantly with this AesSedai MiMo-V2.6-Flash-RL-GGUF model. huggingface.co supports a free trial of the MiMo-V2.6-Flash-RL-GGUF model, and also provides paid use of the MiMo-V2.6-Flash-RL-GGUF. Support call MiMo-V2.6-Flash-RL-GGUF model through api, including Node.js, Python, http.
MiMo-V2.6-Flash-RL-GGUF huggingface.co is an online trial and call api platform, which integrates MiMo-V2.6-Flash-RL-GGUF's modeling effects, including api services, and provides a free online trial of MiMo-V2.6-Flash-RL-GGUF, you can try MiMo-V2.6-Flash-RL-GGUF online for free by clicking the link below.
AesSedai MiMo-V2.6-Flash-RL-GGUF online free url in huggingface.co:
MiMo-V2.6-Flash-RL-GGUF is an open source model from GitHub that offers a free installation service, and any user can find MiMo-V2.6-Flash-RL-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of MiMo-V2.6-Flash-RL-GGUF install, users can directly use MiMo-V2.6-Flash-RL-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
MiMo-V2.6-Flash-RL-GGUF install url in huggingface.co: