Post-training quantization (PTQ) reduces the memory footprint of vision-language-action (VLA) models, but lowering bit widths while maintaining task performance remains challenging. Existing work has used sensitivity estimates from calibration data to assign bit widths to different model components. However, using task success directly to guide mixed-precision allocation is underexplored because closed-loop evaluations are costly and the effect of quantizing one component depends on the precision of other components. To this end, we propose QbD-VLA, a task-guided mixed-precision quantization method that uses task success from short closed-loop evaluations to assign weight and activation bit widths while accounting for interactions between model components. Experiments covering four VLA models and all four LIBERO suites show strong task performance at average precisions of approximately 4 bits for weights and fewer than 6 bits for activations. On SIMPLER, the gain over uniform quantization is small. On a Franka Research 3 robot arm, simulation-selected allocations show no detected success-rate loss on X-VLA but fail on π0.5. These findings support using task success to guide mixed-precision VLA quantization, while highlighting the need for real-world evaluation before deployment. Code is available at github.com/jiuyixu25/QbD-VLA.
Figures & tables
Figure 1: The overview of QbD-VLA. A VLA policy (X-VLA) with one weight / activation bit-width per group and the allocation shown has an effective W4.16 / A5.90 and is deployed unchanged on the FR3 arm. A group is lowered by one level, the policy is rolled out in simulation, and the move is kept only if its success estimate stays above the floor. The search repeats until no move passes.
Policy
Configuration
Spatial
Object
Goal
Long
Avg.
π0.5
Full precision
99.0
99.0
94.0
95.0
96.8
Uniform W4A4
0.0
0.0
0.0
0.0
0.0
Uniform W4A6
97.5
99.5
93.5
95.5
96.5
QbD-VLA W4A5.74
98.5
99.0
94.0
93.5
96.2
OpenVLA-OFT
Full precision
100.0
97.5
96.0
92.5
96.5
Uniform W4A4
0.0
0.0
0.0
0.0
0.0
Table 1: Success rate (%) on the four LIBERO suites. QbD-VLA allocations are selected on LIBERO-Spatial and applied unchanged to the other suites. Their bit widths are parameter-weighted nominal values over all layer groups.
Configuration
W / A
Spatial
Object
Goal
Long
Avg.
FP
16 / 16
99.0
99.0
94.0
95.0
96.8
ActQuant
3.09 / 16
98.5
99.0
97.0
89.0
95.9
HoloQ-VLA
4 / 4
99.0
100.0
96.5
96.5
98.0
QbD-VLA
4.00 / 5.74
98.5
99.0
94.0
93.5
96.2
Table 2: VLA quantization methods on π0.5 under our evaluation on the four LIBERO suites, using their released code or weights. The ActQuant checkpoint averages 3.09 weight bits.
Figure 2: π0.5 rollouts of the LIBERO-Goal task put the wine bottle on the rack from the same initial state. Rows, top to bottom: full precision, uniform W4A4, uniform W4A6, and the QbD-VLA allocation. Uniform W4A4 never approaches the bottle and uniform W4A6 drops it short of the rack, whereas the selected allocation completes the task.
Allocation method
π0.5
OpenVLA-OFT
X-VLA
π0
QbD-VLA
98.5
97.5
97.0
74.5
Action error
27.5
97.5
96.0
76.0
Activation kurtosis
0.0
0.0
0.0
51.0
Reconstruction error
52.0
0.0
91.5
60.0
UFR
99.0
99.0
87.0
68.0
Table 3: Success rate (%) on LIBERO-Spatial. The three sensitivity-based rows share a greedy allocator and the target cost of the QbD-VLA allocation of each policy. UFR reaches its own cost: W4.00 / A5.90, W8.00 / A8.00, W4.00 / A5.62, and W4.00 / A4.54.
X-VLA configuration
W / A
Coke can
Move near
Drawer
Put in drawer
Overall
FP
16 / 16
90.7
84.2
65.7
29.6
75.0
Uniform W4A8
4 / 8
94.0
83.8
64.4
28.7
75.6
Uniform W4A6
4 / 6
87.0
75.4
52.3
4.6
64.8
Uniform W4A4
4 / 4
0.0
1.7
13.9
0.0
3.9
QbD-VLA, 24 tasks, τ=0.90
4.03 / 5.33
87.7
65.8
44.4
0.0
59.8
QbD-VLA, 40 tasks, τ=0.95
4.00 / 5.88
89.3
84.2
43.5
12.0
66.8
Table 4: X-VLA on the SIMPLER visual-matching split.
Model
Configuration
Success
Close cmd.
X-VLA
FP
11/30
28/30
QbD-VLA
13/30
29/30
π0.5
FP
6/6
6/6
QbD-VLA
0/6
0/6
Table 5: Transfer of frozen allocations to the FR3 arm.
Configuration
Success
Close cmd.
Uniform W4A6
0/6
0/6
Uniform W4A8
1/6
1/6
Uniform W8A6
0/6
0/6
Uniform W8A8
5/6
6/6
Table 6: Uniform-precision diagnostics for π0.5 on the FR3 arm.
Figure 3: Some example trials on the FR3 arm.
Model
Group
Layers
Params (M)
Share (%)
QbD-VLA
π0.5
Vision encoder
162
411.1
14.6
W4A6
Language backbone
126
1981.8
70.2
W4A6
Action head: attention projections
72
84.9
3.0
W4A4
Action head: pre-attention modulators
18
56.6
2.0
W4A6
Action head: post-attention and final modulators
18
56.6
2.0
W4A4
Action head: MLP layers
54
226.5
8.0
W4A4
Table 7: Layer groups used for bit allocation, with the number of quantizable linear layers in each group, their parameter count, their share of the model’s quantizable parameters, and the level QbD-VLA selects for the group on LIBERO-Spatial. BF16 and FP32 mark groups kept at the released precision. The All groups rows give the parameter-weighted nominal bit widths used in Table 1 .
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
π0.5
OFT
X-VLA
π0
Released precision
BF16
BF16
FP32
BF16
Render size
360
256
256
360
Action mode
delta
delta
absolute
delta
Halloc
120
120
300
120
Heval , Spatial
280
220
800
280
Heval , Object
280
280
800
280
Appendix
Table 8: Per-model settings. Halloc is the episode limit during allocation and Heval the limit of each model’s official evaluation code, used for every reported number. Allocation episodes and wall-clock time are for the primary LIBERO-Spatial runs.
Mixed-precision quantization assigns different numeric precisions across a model to balance accuracy with memory, speed, energy, and hardware constraints.